diff --git a/mp8/README.md b/mp8/README.md new file mode 100644 index 0000000000000000000000000000000000000000..f3723176551b625d329fee70a75304f3cdc54fd7 --- /dev/null +++ b/mp8/README.md @@ -0,0 +1,55 @@ +# Addition from the Hugging Face team + +> [!IMPORTANT] +> +> This repository corresponds to the original Llama format and codebase, not the transformers library + +The weights were originally distributed in the following format: + +``` +weights/ + consolidated.00.pth + consolidated.01.pth + ... +``` + +Unfortunately, the files themselves were too large for the Hub to handle, so we had to shard them. +In order to keep the same structure that was originally given, the sharding is done as follows: + + +``` +weights/ + consolidated.00/ + consolidated-00001-of-00011.pth + consolidated-00002-of-00011.pth + ... + consolidated.01/ + consolidated-00001-of-00011.pth + consolidated-00002-of-00011.pth + ... + ... +``` + +If trying to run the code that was given with the original weights, we recommend running this script to join the files together once again: + + +```py +import os +import torch + +from pathlib import Path + +path_to_files = Path('.../weights') + +folders = [folder for folder in os.listdir(path_to_files) if os.path.isdir(path_to_files / folder) and folder.startswith('consolidated')] +for folder in folders: + state_dict = {} + files = [file for file in os.listdir(path_to_files / folder) if file.endswith(".pth")] + + for file in files: + state_dict_partial = torch.load(path_to_files / folder / file, map_location="cpu") + for key, value in state_dict_partial.items(): + state_dict[key]=value + + torch.save(state_dict, path_to_files / f"{folder}.pth") +``` diff --git a/mp8/consolidated.00/consolidated-00001-of-00022.pth b/mp8/consolidated.00/consolidated-00001-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a78a20f3136649a401ebcc83c64bd3104f6d419 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00001-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82a24725af2c501bd3f6eaef1317178dd1cf91b743d235b8aad4241f911ed73e +size 4870980313 diff --git a/mp8/consolidated.00/consolidated-00002-of-00022.pth b/mp8/consolidated.00/consolidated-00002-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..440566cc92e2fcf27b415b90895851e68ef8e241 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00002-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84eefbc1e4af3dcc0bff6e6826f0faac3a7ddb6db8589229107be48f5a891089 +size 4781917812 diff --git a/mp8/consolidated.00/consolidated-00003-of-00022.pth b/mp8/consolidated.00/consolidated-00003-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..274f2719837b193d247f531798dc21d78862d8ab --- /dev/null +++ b/mp8/consolidated.00/consolidated-00003-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77e8d2c3b14116d3b7ed57faebe98e184a67e36727b3dddef50fe8734f7cc254 +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00004-of-00022.pth b/mp8/consolidated.00/consolidated-00004-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b381c5f8d0f20c30910e1a280894c2d521932e6 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00004-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21852544089ff9f59977d649a7e89e8c58ef27f3dff5b1f3c29d9f7569a74a9e +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00005-of-00022.pth b/mp8/consolidated.00/consolidated-00005-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..dbd4e2c0bbda48942a8325a3558c581bcdc05a9c --- /dev/null +++ b/mp8/consolidated.00/consolidated-00005-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6fa844698a04650c32073af9dd275beed5709420cd7b01250d8d7acba970f9a +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00006-of-00022.pth b/mp8/consolidated.00/consolidated-00006-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..786a9a2bcc30aaba9c4c5fdd5751a3849e6ce295 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00006-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a8379326f7edd6cad430b2825277be0f2832db4f41bbeb883060255465ae32 +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00007-of-00022.pth b/mp8/consolidated.00/consolidated-00007-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4ad8e967696b1eae6b5c70e794a456541246a3a --- /dev/null +++ b/mp8/consolidated.00/consolidated-00007-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:276ce60c24d09a455ca3b63b87d529c6d1cf96ba6818f3b03352e23f3239c7ff +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00008-of-00022.pth b/mp8/consolidated.00/consolidated-00008-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..2cfd7484ad7bb1f90efc0e9238b1df91f0c82a8e --- /dev/null +++ b/mp8/consolidated.00/consolidated-00008-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb29ad62d70fcd3398ebe9e1d0f9543d040ce30423120a22a914fcdc8d34bd5 +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00009-of-00022.pth b/mp8/consolidated.00/consolidated-00009-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..8035af0321dfcf69e00b9f85c382bea9dc393196 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00009-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0271f28e0655a3aee18fd7081ac84efd41cbf81a3f1d040c65653df7db5dd3de +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00010-of-00022.pth b/mp8/consolidated.00/consolidated-00010-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..20065c8ceade5d23f2f48d40cd9b7a7c5e5b30ec --- /dev/null +++ b/mp8/consolidated.00/consolidated-00010-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cbf1e3b9ae8c552e8cb47908066a88af1a8ec91b9b06432338b65932105412f +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00011-of-00022.pth b/mp8/consolidated.00/consolidated-00011-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9c7726b4ed3434fef651b26fdbffb9f0ecd5360 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00011-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb369294f30262130ec04f9455b87502e99e4826fbac15d346b905858a3e72cb +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00012-of-00022.pth b/mp8/consolidated.00/consolidated-00012-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..51eaf097063b0d38cfab6cbcc69f6d80c42b5a78 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00012-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e938f8a6fbca2931db1003a7eb2dfd439c033396f7828e23ada11dc5de58d86 +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00013-of-00022.pth b/mp8/consolidated.00/consolidated-00013-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..6db31bd9fd0e09ccee6cbc12eda964992ab5bf11 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00013-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d625497096c62c74f1ced1b310316c2bfcc1ebbff61c52cec637cecafa27a0 +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00014-of-00022.pth b/mp8/consolidated.00/consolidated-00014-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e8ffff35ab66078b6589750312be15bb41a80674 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00014-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8cfae88c9ba58b2a1ebdd1608c899af26ca35d6a279f5c06894953a01ef298 +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00015-of-00022.pth b/mp8/consolidated.00/consolidated-00015-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..adda62aefc3632b5e37b94357c167763b49b6f59 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00015-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ec81131f61b758cec0a480bf3203361acc140b45e3b7abd759462b4cf90ce0 +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00016-of-00022.pth b/mp8/consolidated.00/consolidated-00016-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc642c0202eac67642596faf104d93253dea6ec9 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00016-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1d7debe2480ce2ee37dfe49569f4ff3f39d75a89d0af64bebd37e0ad4e8d56a +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00017-of-00022.pth b/mp8/consolidated.00/consolidated-00017-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..660f83d2fae3d417d7cf2df2fdfc3a06326a7b4c --- /dev/null +++ b/mp8/consolidated.00/consolidated-00017-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9bc5d9023afddd4025f9d648e5ebdcfe35f8b34f1e3e5dd921e134b8e085b28 +size 4781917876 diff --git a/mp8/consolidated.00/consolidated-00018-of-00022.pth b/mp8/consolidated.00/consolidated-00018-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..7021da10b8ece9aba271197b04c76a18ad583354 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00018-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e020419201c24c679ac12ec5753085d039e3811a7352d916e80b66f52f677a +size 4781917940 diff --git a/mp8/consolidated.00/consolidated-00019-of-00022.pth b/mp8/consolidated.00/consolidated-00019-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..391966da490eaba2c642a5df754cbb7fe1eae345 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00019-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2490891133dda2a05ece4195532c9caf1f7f5a0cd0c7753f1a4bd145da442605 +size 4781917940 diff --git a/mp8/consolidated.00/consolidated-00020-of-00022.pth b/mp8/consolidated.00/consolidated-00020-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..37730b9479f2ab107c552179fc415e44308f0adc --- /dev/null +++ b/mp8/consolidated.00/consolidated-00020-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec43066f0ddf7dfc5218f6edb252575e24bfc6c0aea0f603a27b3999d2d1376 +size 4781917940 diff --git a/mp8/consolidated.00/consolidated-00021-of-00022.pth b/mp8/consolidated.00/consolidated-00021-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..0183bdb8369d94665f539ac6204513c0e9cc21c2 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00021-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d0553a5241926349bc20d86fe91948c4e6f0c1f5521f3e97deead0d81f0a16 +size 4781917940 diff --git a/mp8/consolidated.00/consolidated-00022-of-00022.pth b/mp8/consolidated.00/consolidated-00022-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..248d8056bbdcf90d767d2a94f03511d9fc355943 --- /dev/null +++ b/mp8/consolidated.00/consolidated-00022-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459bd4b1e50693ad120500b71ab361225ae6db2506a0da2cccf8a6dc5427df98 +size 961645392 diff --git a/mp8/consolidated.00/consolidated.pth.index.json b/mp8/consolidated.00/consolidated.pth.index.json new file mode 100644 index 0000000000000000000000000000000000000000..28b4564cf4f84c2b1efcd25219dd769b659fa5a6 --- /dev/null +++ b/mp8/consolidated.00/consolidated.pth.index.json @@ -0,0 +1,1144 @@ +{ + "metadata": { + "total_size": 101470601216 + }, + "weight_map": { + "tok_embeddings.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth", + "layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth", + "layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth", + "layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth", + "norm.weight": "consolidated-00022-of-00022.pth", + "output.weight": "consolidated-00022-of-00022.pth" + } +} \ No newline at end of file diff --git a/mp8/consolidated.01/consolidated-00001-of-00022.pth b/mp8/consolidated.01/consolidated-00001-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..b06a108bc0bfe9caedbf026b7ab5f682cdb28ba9 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00001-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b8ed18e98b6f7c89e658fb8b621130dfc6c3f14edbe4db358bd208531f35a8 +size 4870980313 diff --git a/mp8/consolidated.01/consolidated-00002-of-00022.pth b/mp8/consolidated.01/consolidated-00002-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..529097f2cf503461187a7596822bb8e0fe0dc4f2 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00002-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1df5fe20eee3c697c148881613e00e2081494afec233caf38e3bb54fc6511c +size 4781917812 diff --git a/mp8/consolidated.01/consolidated-00003-of-00022.pth b/mp8/consolidated.01/consolidated-00003-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..56626bc232c290d1a9a4ba1249e0f504ee555d27 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00003-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a201321342f264778eef1fdc59a5c7b88cc2fcb67e11ce6641ca72479afce91 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00004-of-00022.pth b/mp8/consolidated.01/consolidated-00004-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac6e730cbead671e4aed7c023b91d0cd9e9a42b5 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00004-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c80392b2bb693076a9e02bb6f1a1ace8f57dd814b473d2adb8c9ae34661575 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00005-of-00022.pth b/mp8/consolidated.01/consolidated-00005-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..63e2b3ed2a858422af4252dc75e3b6b4f8ad1f9f --- /dev/null +++ b/mp8/consolidated.01/consolidated-00005-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49539bfb3b19024ba153e12573b389920921497c0687ff14b9941fdaecffa38 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00006-of-00022.pth b/mp8/consolidated.01/consolidated-00006-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..b88d0b583e415bb1a57fe2f178ea4d891ecd38e3 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00006-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1221a187cc2d4e4ff7f93bc8ff67332e0f8f3be744f0329f25029f1df464e6bb +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00007-of-00022.pth b/mp8/consolidated.01/consolidated-00007-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed52e43b7440c720a91b1d4e4fdf4ffd2e198312 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00007-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33bf1b298d08b30e2809cfc8f347b8baf017b9b0b607f4626ae99f9d39b0fd46 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00008-of-00022.pth b/mp8/consolidated.01/consolidated-00008-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..7bdd0db8d46f30e82830155a3c40c2806d52e90d --- /dev/null +++ b/mp8/consolidated.01/consolidated-00008-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5986e4fafcee216c764a57c4d804aa78f9df741d3ba418a6c9fb2a3f088ea563 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00009-of-00022.pth b/mp8/consolidated.01/consolidated-00009-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..68562b0ee7e254227ecd58eb8e0c33f91d967316 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00009-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a634319106e14cc7ab901db880eeaa144d0834fcc4241b64bf5448e9b94366 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00010-of-00022.pth b/mp8/consolidated.01/consolidated-00010-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..96efcec2b6d4be86518d64d6aeb838a93777ccc1 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00010-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b299dac7e7cdcba57f57c9aeedd435bd8eee047eff455b510dfa120136b19a +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00011-of-00022.pth b/mp8/consolidated.01/consolidated-00011-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee515104f8cb18b5a9e65389b199cc6fc75175c9 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00011-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e42ee90016b0c3dcbca38251a09d486872110a7b4ea0f75183d473f4c500228 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00012-of-00022.pth b/mp8/consolidated.01/consolidated-00012-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..b903fd13208df81291de97fe300b30dca0b577bb --- /dev/null +++ b/mp8/consolidated.01/consolidated-00012-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef9e647d3c4f9a7187c89ccb27d4193d0525f1048c77a414ee95f84bd2199bf6 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00013-of-00022.pth b/mp8/consolidated.01/consolidated-00013-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd89156fba00a6ba34a0bdea9e6972386650a238 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00013-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fecf04787997fe38665672feb4d47609c51d29b7b78e3c3b767d88f48df886a +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00014-of-00022.pth b/mp8/consolidated.01/consolidated-00014-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..8df8ca389f61e8b2e4e60a83a09fd15a049dd6e9 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00014-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96313c3901d234e556059f60a6901d2f299e347380467eda38aa227acd425b8b +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00015-of-00022.pth b/mp8/consolidated.01/consolidated-00015-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..242b57ab294bc4fe977391726212631413c57fe4 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00015-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9c3f9b5dbac9bae7257b272ab1abcd1dd1155529e6f8faf1f7a9607fc08588b +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00016-of-00022.pth b/mp8/consolidated.01/consolidated-00016-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..a467517c0d80e985573ef5a48d8a84ffe9546ff2 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00016-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7a1e03121865bafde2cb3c5fa24c0ea701cd24f024bf63f9c6eef7a2d9474e +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00017-of-00022.pth b/mp8/consolidated.01/consolidated-00017-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..1858358404c8550fbc3a455df852b7cd93f8a12e --- /dev/null +++ b/mp8/consolidated.01/consolidated-00017-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87ea70c86c6fb777c370e4a6a96b63c4a1c55e77a3e2d16f5701f0ce52a3d002 +size 4781917876 diff --git a/mp8/consolidated.01/consolidated-00018-of-00022.pth b/mp8/consolidated.01/consolidated-00018-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3125726a20fb2b5fa06a9adf41593bfafd5f632 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00018-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1d004153f11e21398f3e792df15109700069c80fea3d0d5cba4500ba032a52 +size 4781917940 diff --git a/mp8/consolidated.01/consolidated-00019-of-00022.pth b/mp8/consolidated.01/consolidated-00019-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d424641bce4780040c60b6bb911b8909b152a9f0 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00019-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9f6538fabaf05f5c9b38038f273c87e222052cb599bbd7957c09738de90d186 +size 4781917940 diff --git a/mp8/consolidated.01/consolidated-00020-of-00022.pth b/mp8/consolidated.01/consolidated-00020-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..705be68ea87b278aff1d7c2f05d27e6e0da93e24 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00020-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e07fff1b27685c5b4817bd434e91e56ebbf15002858e662640c82d6deccd35ef +size 4781917940 diff --git a/mp8/consolidated.01/consolidated-00021-of-00022.pth b/mp8/consolidated.01/consolidated-00021-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..de73661cc5f600d73bde20e7684a571e6d86ecd4 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00021-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bef0f8aa540ebe150c0448ba0a46378f4ede0f63bb141f99752723348b7eecf +size 4781917940 diff --git a/mp8/consolidated.01/consolidated-00022-of-00022.pth b/mp8/consolidated.01/consolidated-00022-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f2664d73da3b873c18a588d87f7d0ea86e1e0d2 --- /dev/null +++ b/mp8/consolidated.01/consolidated-00022-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21924772fa394ee7270e99afbefad33c18276900201595696e4c988d8b5a0e96 +size 961645392 diff --git a/mp8/consolidated.01/consolidated.pth.index.json b/mp8/consolidated.01/consolidated.pth.index.json new file mode 100644 index 0000000000000000000000000000000000000000..28b4564cf4f84c2b1efcd25219dd769b659fa5a6 --- /dev/null +++ b/mp8/consolidated.01/consolidated.pth.index.json @@ -0,0 +1,1144 @@ +{ + "metadata": { + "total_size": 101470601216 + }, + "weight_map": { + "tok_embeddings.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth", + "layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth", + "layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth", + "layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth", + "norm.weight": "consolidated-00022-of-00022.pth", + "output.weight": "consolidated-00022-of-00022.pth" + } +} \ No newline at end of file diff --git a/mp8/consolidated.02/consolidated-00001-of-00022.pth b/mp8/consolidated.02/consolidated-00001-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6e2db0d4d13f3ccdad63950c766c644064a1ee5 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00001-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a74d2dd5b327ef9e529eb5010a5490270849c4b0eb1a8e6b9b2ff64519f40af +size 4870980313 diff --git a/mp8/consolidated.02/consolidated-00002-of-00022.pth b/mp8/consolidated.02/consolidated-00002-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..938fa2d61e441aad3868ce1b37a8a534c96a0f7e --- /dev/null +++ b/mp8/consolidated.02/consolidated-00002-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0210b8d092c04f3215430912ee65d75a1d62150893b1f254b614edc6e6ee55 +size 4781917812 diff --git a/mp8/consolidated.02/consolidated-00003-of-00022.pth b/mp8/consolidated.02/consolidated-00003-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..bc0f187c6c108c73ffadff449858469b6b565639 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00003-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb410b976be6349162eeb5ab74c03836d39d05c0b781cc73ff829fb7e099066f +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00004-of-00022.pth b/mp8/consolidated.02/consolidated-00004-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e9c4bcba4dc425364e4ccb266bd5274fcdaddaa --- /dev/null +++ b/mp8/consolidated.02/consolidated-00004-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3995f1c23ea6c32cacbd2bda5d52329a5a5ff35f18527e33932aaea0d1381c2a +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00005-of-00022.pth b/mp8/consolidated.02/consolidated-00005-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4d2b0c776320aca4cfbba8f95d5d0a733ece3aa --- /dev/null +++ b/mp8/consolidated.02/consolidated-00005-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa47ba158fb5666904825a002b9e7ec5823eb85c41153957373ed4642677a8ed +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00006-of-00022.pth b/mp8/consolidated.02/consolidated-00006-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..6c39ef69e0c6ee32d9ccd9b9ad56eacfb31cd036 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00006-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43f1bf08b248f2cda446afe7a3e3156fdd0d143659ff607dcc1e209c21856ff +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00007-of-00022.pth b/mp8/consolidated.02/consolidated-00007-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..713f991b27a2619a66bca93ed5867437d32bac4b --- /dev/null +++ b/mp8/consolidated.02/consolidated-00007-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd788f0d5092eabf8e76bde97a19eb54800d28ab7081056a8ec56947495f78f +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00008-of-00022.pth b/mp8/consolidated.02/consolidated-00008-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..579f374fb49742013c145c9764f1e4e31cf0657b --- /dev/null +++ b/mp8/consolidated.02/consolidated-00008-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d079ffa49072d97490efabf707b4e3f7dcc279b528948d3ea2cbb17b23250c +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00009-of-00022.pth b/mp8/consolidated.02/consolidated-00009-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..251159774d71216d0a175f6b5c6249828a8b2192 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00009-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e62ee6f709ed4c1666db9fd968c2ebb7948fe7150e61ad5147bd7e7f9e6ca46 +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00010-of-00022.pth b/mp8/consolidated.02/consolidated-00010-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..987c8c2066c75e5b1102566148adb5dc80f33b80 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00010-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03c17eb7a15d1bd44573b9f3d611e438e36eb0513fcfb8f9b6db8a5cd630de8 +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00011-of-00022.pth b/mp8/consolidated.02/consolidated-00011-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..da75c88a03ccb11a5f46785657866da9f8074120 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00011-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70136e306b9a18e28555f51e77b3283702abdfa1b872d22c6f70e19b2ecedcbc +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00012-of-00022.pth b/mp8/consolidated.02/consolidated-00012-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..1a5367b4bda9691f68097b1a2b5d9fce9c89eca4 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00012-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e049b8dd5cab730f057e3c5935f17ea61ed50f9c9a4ae71ea5143e34dd08e77 +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00013-of-00022.pth b/mp8/consolidated.02/consolidated-00013-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3ed3a66183b87e7f10758095c81d8da533eefb6 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00013-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a9c9b9b52201ba1ebd243ba61c8e7ef415bf448e0dc2e59bc70f4e37ef5822 +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00014-of-00022.pth b/mp8/consolidated.02/consolidated-00014-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d0e2972c37ddc689a443df857cbf72e1a7261d82 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00014-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389e2b57592842d1c7bb2980efad510d959161fc8d25d98a3c6803df95096f3f +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00015-of-00022.pth b/mp8/consolidated.02/consolidated-00015-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..598018891ae45a351de85ad78bd3540e024145bf --- /dev/null +++ b/mp8/consolidated.02/consolidated-00015-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b01fd1c2eb67ec690cf3fc2856a704254b421a01afbe89126f37af9330faa3bd +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00016-of-00022.pth b/mp8/consolidated.02/consolidated-00016-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..60dec187d3d96412cd2aad0e24ecc486849e64f1 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00016-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af27c90c2c6cc2139d9009bdf1ec988e629c1692f605aa1df26526cfcf9bba8c +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00017-of-00022.pth b/mp8/consolidated.02/consolidated-00017-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..28b3a43d91b02a520e0bcc42dc25e72e98a2434b --- /dev/null +++ b/mp8/consolidated.02/consolidated-00017-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d361b214ff104240ba8fb448213a887d87b2b72082454d7fba69527b065db70 +size 4781917876 diff --git a/mp8/consolidated.02/consolidated-00018-of-00022.pth b/mp8/consolidated.02/consolidated-00018-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e6a2a6b13cc1c9ba2bdf19ca9a833d5ddd910628 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00018-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354aadeb6ec7ca97c7b600215c18e1efbc4a31b2accd3d5cc9a78f8f5e9d207c +size 4781917940 diff --git a/mp8/consolidated.02/consolidated-00019-of-00022.pth b/mp8/consolidated.02/consolidated-00019-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3881f9a8c21adce14219a1dc9b3f131892ae81e --- /dev/null +++ b/mp8/consolidated.02/consolidated-00019-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de540345374691c6a4903e5879cf98ab21e1deef6f0da1d787cd3d2d36cb819 +size 4781917940 diff --git a/mp8/consolidated.02/consolidated-00020-of-00022.pth b/mp8/consolidated.02/consolidated-00020-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e228603f4d8793decb45f410e82e2b1a431f4d19 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00020-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f76aaa209aafd8a74fe1d1f79257673b1ba17e476cc44e83aa1abe02c8acfe6 +size 4781917940 diff --git a/mp8/consolidated.02/consolidated-00021-of-00022.pth b/mp8/consolidated.02/consolidated-00021-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..79eaf045e2a1760fc02dff4d27b5b70d08c52ff4 --- /dev/null +++ b/mp8/consolidated.02/consolidated-00021-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:439b1f60a47d55ccdfd4b28593e926af10c9d3eadec9b029b5fd65cf08b7d374 +size 4781917940 diff --git a/mp8/consolidated.02/consolidated-00022-of-00022.pth b/mp8/consolidated.02/consolidated-00022-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..bed6220f33c4e2dc2801f15e94fe1714d92bff1c --- /dev/null +++ b/mp8/consolidated.02/consolidated-00022-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8adc9fdb9da7970a89f14a347a679197bb6040e17513cb6641f4492a988e6cf7 +size 961645392 diff --git a/mp8/consolidated.02/consolidated.pth.index.json b/mp8/consolidated.02/consolidated.pth.index.json new file mode 100644 index 0000000000000000000000000000000000000000..28b4564cf4f84c2b1efcd25219dd769b659fa5a6 --- /dev/null +++ b/mp8/consolidated.02/consolidated.pth.index.json @@ -0,0 +1,1144 @@ +{ + "metadata": { + "total_size": 101470601216 + }, + "weight_map": { + "tok_embeddings.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth", + "layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth", + "layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth", + "layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth", + "norm.weight": "consolidated-00022-of-00022.pth", + "output.weight": "consolidated-00022-of-00022.pth" + } +} \ No newline at end of file diff --git a/mp8/consolidated.03/consolidated-00001-of-00022.pth b/mp8/consolidated.03/consolidated-00001-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..abfd26bcec240d1d30823d7606025e3440f0eff2 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00001-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da5c06993e4e18da86d05ea571dd53ace05e46e5ab1127d84906449e3976f549 +size 4870980313 diff --git a/mp8/consolidated.03/consolidated-00002-of-00022.pth b/mp8/consolidated.03/consolidated-00002-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c852f9299995d9f425e0aa5891afa26535c7be1 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00002-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ae34554e38e96acf4759f6ab74c9ef463783c401e2b53f1fe647cac12a0678 +size 4781917812 diff --git a/mp8/consolidated.03/consolidated-00003-of-00022.pth b/mp8/consolidated.03/consolidated-00003-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..aea782738bfa81f3e775ba8f15ef3c3a164f45bd --- /dev/null +++ b/mp8/consolidated.03/consolidated-00003-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c4b47cc75dc46b8168e00080b895fc9802cf93f04121de3fa026143d3edc8c +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00004-of-00022.pth b/mp8/consolidated.03/consolidated-00004-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..be52a925f59664251e8399f7933dcfae75eec565 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00004-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e488f6f754be8923d725a3b1eb2bc116e9a2cd1bc70708d90403b5d85cbba02d +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00005-of-00022.pth b/mp8/consolidated.03/consolidated-00005-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..f1217229f07b34f858bf70a44704977e9c590c88 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00005-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd2678bc55a5f05e18785a51e315320e2f7d5432fc9a5a9913cd682315597c8 +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00006-of-00022.pth b/mp8/consolidated.03/consolidated-00006-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..6af1a7454994fd978a1fd56c4d17f8b8e4fb97f4 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00006-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3153081213e8a284e199b598d589d4d4ffc066d016c1cf87be588442a10458 +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00007-of-00022.pth b/mp8/consolidated.03/consolidated-00007-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..071f82b1b7f514f7373e8626753c5133534688b6 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00007-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937eae1d6e14627aecc96be5f47604ede7de2424e09c3d4271f5b1c54b5e8eb6 +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00008-of-00022.pth b/mp8/consolidated.03/consolidated-00008-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..861fc91c87bdc22a798fc8d4eef69c4280a90230 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00008-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc1df3ecb3fa71e7a19096107c8db1f9c45e3c7bb10e46e8931fbd0d1218f0d +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00009-of-00022.pth b/mp8/consolidated.03/consolidated-00009-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..f1d713b413990bac9e408b2b114349caa389ca41 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00009-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f8b3d9d662deafa6d05a66bea8733a5ccc951f230c0018df9c783cc86645c5a +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00010-of-00022.pth b/mp8/consolidated.03/consolidated-00010-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c1c78345ef9031fec93c51375f0eeb879ae03a4 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00010-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add8c8a066f8b34274b8f20273307512aa8e631aeef8f9fba80969b9acb8f6fe +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00011-of-00022.pth b/mp8/consolidated.03/consolidated-00011-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..4dcb84728867be7d41811cbc917ecac749f232c8 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00011-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9dfd85037fcfb0e5bd1512ae1554a4598d663e8ae854780d2016e844cd6826 +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00012-of-00022.pth b/mp8/consolidated.03/consolidated-00012-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab677a28b39cb69034a8ef89267c42176105d0bc --- /dev/null +++ b/mp8/consolidated.03/consolidated-00012-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb4acb132252604317a21155b6243bac69d1ba446cfd340d81f6c0cc31b4c0c +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00013-of-00022.pth b/mp8/consolidated.03/consolidated-00013-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac4deb6a36e13148fa973835c528f2db809fb482 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00013-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b4e0079ca311861ae15affafb099deb3a8d81d3bdbc29820083b1824f5d849 +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00014-of-00022.pth b/mp8/consolidated.03/consolidated-00014-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7b4baa58ce8c5bb44c626fffa7586e4356fb2bb --- /dev/null +++ b/mp8/consolidated.03/consolidated-00014-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0342cfe5ce754e85fc98c3e9b89a258dd82603cdb1512101dd9628957441ded +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00015-of-00022.pth b/mp8/consolidated.03/consolidated-00015-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9d9d604d66e8256005d2862d1c6c8cc2c16e33f --- /dev/null +++ b/mp8/consolidated.03/consolidated-00015-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4c0b7f2919a11f4eb68141ef1ec0b1c02b9f0f0321aeb0947a35791050454b +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00016-of-00022.pth b/mp8/consolidated.03/consolidated-00016-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..6261e96b98a1055147c6dd896d7e64a2f9fbf0dd --- /dev/null +++ b/mp8/consolidated.03/consolidated-00016-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:263098b2896e3a85f90e81dd11506f532f038e2c354d774f72da88e55d7659db +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00017-of-00022.pth b/mp8/consolidated.03/consolidated-00017-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..0963e03c555c9497f5a2e998d1f656f6a395b7fb --- /dev/null +++ b/mp8/consolidated.03/consolidated-00017-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbfa95ec32940289c17e6dc2b01c7708b05a3e87cc032bf3d6e8220977402022 +size 4781917876 diff --git a/mp8/consolidated.03/consolidated-00018-of-00022.pth b/mp8/consolidated.03/consolidated-00018-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d681f8ba449f7b50d91ea0680316dc0811fa22e1 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00018-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e5c3a5fc6ca6b3d98777247dab6fbeaec6734d38e1f09eeb37346ec367a2de +size 4781917940 diff --git a/mp8/consolidated.03/consolidated-00019-of-00022.pth b/mp8/consolidated.03/consolidated-00019-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..5380e152428177cca1bc8ed55c2b7ace117bb460 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00019-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6009fc7c50421bd73759b9ffe41ad89508f094a3a48a5d2af67fa532eb8a275a +size 4781917940 diff --git a/mp8/consolidated.03/consolidated-00020-of-00022.pth b/mp8/consolidated.03/consolidated-00020-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..efd41559450b0f06871ad50225e5c22ac7b1aa37 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00020-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e9e5ce55c4f69729f26df0f8004952993ace853ffcc5eaa8ac7aef09799a9b +size 4781917940 diff --git a/mp8/consolidated.03/consolidated-00021-of-00022.pth b/mp8/consolidated.03/consolidated-00021-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..20c598d66d25fc58929667e37034e582ac8aef51 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00021-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820f1944f2f1b71d33a1660b4a74b0ad0de95bc081e6c2968ea56a781f9bb7ca +size 4781917940 diff --git a/mp8/consolidated.03/consolidated-00022-of-00022.pth b/mp8/consolidated.03/consolidated-00022-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3400f1abd22b7a18dae39b41011e8cb168e3948 --- /dev/null +++ b/mp8/consolidated.03/consolidated-00022-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5470464a1864586410f2f7b6af375fd3efac57b24c9b62c82dbf7e4715830f67 +size 961645392 diff --git a/mp8/consolidated.03/consolidated.pth.index.json b/mp8/consolidated.03/consolidated.pth.index.json new file mode 100644 index 0000000000000000000000000000000000000000..28b4564cf4f84c2b1efcd25219dd769b659fa5a6 --- /dev/null +++ b/mp8/consolidated.03/consolidated.pth.index.json @@ -0,0 +1,1144 @@ +{ + "metadata": { + "total_size": 101470601216 + }, + "weight_map": { + "tok_embeddings.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth", + "layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth", + "layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth", + "layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth", + "norm.weight": "consolidated-00022-of-00022.pth", + "output.weight": "consolidated-00022-of-00022.pth" + } +} \ No newline at end of file diff --git a/mp8/consolidated.04/consolidated-00001-of-00022.pth b/mp8/consolidated.04/consolidated-00001-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..3367f4378b04c9bf3e1e9cf6663b45fa778818e6 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00001-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3245c264cbd01a42699c20e01cd007916f9ef2a7a99e775918fa0cdfdc0f2a2a +size 4870980313 diff --git a/mp8/consolidated.04/consolidated-00002-of-00022.pth b/mp8/consolidated.04/consolidated-00002-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e1eda34ddc227d4a3101ff1600ee31848c6de83b --- /dev/null +++ b/mp8/consolidated.04/consolidated-00002-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78211f09d7b960d00b215b101c8f157900ff3174aab261f3680035eaa7493d4e +size 4781917812 diff --git a/mp8/consolidated.04/consolidated-00003-of-00022.pth b/mp8/consolidated.04/consolidated-00003-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..722ef5bd2aba4441eeec5deb26ffcd1e3b6eb6f0 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00003-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2396f14e40a9776ee9df8c9d1ee00007b27e22fac2105be7374af5d17fca657c +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00004-of-00022.pth b/mp8/consolidated.04/consolidated-00004-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..af3ad357cd8bc77f42771897901652517e38d521 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00004-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a075683b5e9b499c2ca43ab6823352efdf4d4d6c773e85635046991c1109cf7 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00005-of-00022.pth b/mp8/consolidated.04/consolidated-00005-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..7fca167437a125d14af4e96d2df58337cfdcdb06 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00005-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b2559fd5803946b85fe4e28859bd50165c3fce56cf095352566564129ef18a +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00006-of-00022.pth b/mp8/consolidated.04/consolidated-00006-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa0a6c1d64765245a4febda7e365d05603100044 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00006-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea6792dc0e54e37a78b272d09101e51063575dac2ecb7cd310830ac47cd2214 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00007-of-00022.pth b/mp8/consolidated.04/consolidated-00007-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..cde1eab8d3353e84f244330ea3193388ab715ccf --- /dev/null +++ b/mp8/consolidated.04/consolidated-00007-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dab1b8fd2807cd95af4f5dc029e16fb163fc266f0b370bd481831702da0cd51 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00008-of-00022.pth b/mp8/consolidated.04/consolidated-00008-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..80ff850bef8fdf5eea27eed7c503aa4aeaa91b5d --- /dev/null +++ b/mp8/consolidated.04/consolidated-00008-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9949909be66862afe8e1074805c5d709ed08f6417b7107ae4cb32e7b043db8c7 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00009-of-00022.pth b/mp8/consolidated.04/consolidated-00009-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..69b5a8ae71f688a01ab87aede6774c388894a3fa --- /dev/null +++ b/mp8/consolidated.04/consolidated-00009-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176ea21508febeedb0b81167291f873b2534e84acbbe283c103bb84e952953bb +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00010-of-00022.pth b/mp8/consolidated.04/consolidated-00010-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5229de1464c2d6ecb44cfc22514f29eec578a18 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00010-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1afae1b3cd9d9f013d5095fa69046f475c48b879964f5bb39c3b688fdc1164 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00011-of-00022.pth b/mp8/consolidated.04/consolidated-00011-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..039d24180bbe3be63acb4f6682dc878dce173137 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00011-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d49b84c406344c6408377df850c0f2678aaa2ee74162bfd7ef674351ae9a96 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00012-of-00022.pth b/mp8/consolidated.04/consolidated-00012-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb26ca6abef41b287405fd127403dcf220858b92 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00012-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5248d056af54d403d85d1a7afadf50fdaa8a77542a3567f5994877115beff3 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00013-of-00022.pth b/mp8/consolidated.04/consolidated-00013-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec7dd601ba35433b14118c13c4edac66fd98d0fa --- /dev/null +++ b/mp8/consolidated.04/consolidated-00013-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a3593bb04b352a442f883a2226df9f70d49cffa0245ec45a799b5b086d8029 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00014-of-00022.pth b/mp8/consolidated.04/consolidated-00014-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..cbcb8c03c0666775cbdbc1ed94dfba3954f423b8 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00014-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a15e69547bc4ea1539b818f31ca93edac8783753341e14294013023afc57591 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00015-of-00022.pth b/mp8/consolidated.04/consolidated-00015-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..9cc27154e14db2708e2804c9efd7ec1665ca7ce1 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00015-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8634be30a2204e5a54fbbd9a80988e8a860e99d2ffb6e649ba5034daef23e967 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00016-of-00022.pth b/mp8/consolidated.04/consolidated-00016-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..010479bd6318f474027946effc87c54305222be6 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00016-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4bba259322a0864084703d0dc3792308f6b6aa8ecabbada7936ec4dcabbe7ed +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00017-of-00022.pth b/mp8/consolidated.04/consolidated-00017-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d429e8c4401df5687c7c0db3dd6a34537492a841 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00017-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2154fa6dbf2622801012a30b9584fe3ca438ace72cfdd26851db1c17331f6a78 +size 4781917876 diff --git a/mp8/consolidated.04/consolidated-00018-of-00022.pth b/mp8/consolidated.04/consolidated-00018-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..edb051caac6fe3118b802e362e50515a0442159c --- /dev/null +++ b/mp8/consolidated.04/consolidated-00018-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8717535cc2cd8f3eea3880f53b99bb12613cbc4c7a8aaf1f5132a8e3217252 +size 4781917940 diff --git a/mp8/consolidated.04/consolidated-00019-of-00022.pth b/mp8/consolidated.04/consolidated-00019-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..23edd6871b8ad863babb290661b447592642ac46 --- /dev/null +++ b/mp8/consolidated.04/consolidated-00019-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d42df477559923ff68aec7e04023cafc0f71e4bb03c36db67e2a52d8ebb345e7 +size 4781917940 diff --git a/mp8/consolidated.04/consolidated-00020-of-00022.pth b/mp8/consolidated.04/consolidated-00020-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad138b185e89bc2ad2409898a7879cd86a17903f --- /dev/null +++ b/mp8/consolidated.04/consolidated-00020-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c84e4e3f9bd0c4e81aa40b082e4544276c62d3c8ec460b5b72b82734a349e30a +size 4781917940 diff --git a/mp8/consolidated.04/consolidated-00021-of-00022.pth b/mp8/consolidated.04/consolidated-00021-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..89b50892c8f2d8c6ed117763d8d590a04691149b --- /dev/null +++ b/mp8/consolidated.04/consolidated-00021-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd809b4620bdbad262204231c0686ada76071801bec4de6d1233bea7e9a88edf +size 4781917940 diff --git a/mp8/consolidated.04/consolidated-00022-of-00022.pth b/mp8/consolidated.04/consolidated-00022-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..6c7949c07d298aa36e8fd77ad5aa21d7053c4e8b --- /dev/null +++ b/mp8/consolidated.04/consolidated-00022-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4e381d439d03b6f5cf46e02e104bfd58f9e66cc04f4455b3af873ba33204d0 +size 961645392 diff --git a/mp8/consolidated.04/consolidated.pth.index.json b/mp8/consolidated.04/consolidated.pth.index.json new file mode 100644 index 0000000000000000000000000000000000000000..28b4564cf4f84c2b1efcd25219dd769b659fa5a6 --- /dev/null +++ b/mp8/consolidated.04/consolidated.pth.index.json @@ -0,0 +1,1144 @@ +{ + "metadata": { + "total_size": 101470601216 + }, + "weight_map": { + "tok_embeddings.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth", + "layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth", + "layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth", + "layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth", + "norm.weight": "consolidated-00022-of-00022.pth", + "output.weight": "consolidated-00022-of-00022.pth" + } +} \ No newline at end of file diff --git a/mp8/consolidated.05/consolidated-00001-of-00022.pth b/mp8/consolidated.05/consolidated-00001-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e6abf2d8ace5e36648796f739c1ad58e0f76393e --- /dev/null +++ b/mp8/consolidated.05/consolidated-00001-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be898a95926cf45ddea01632f8034c2ddbf4984b2da551721c7304729aa43688 +size 4870980313 diff --git a/mp8/consolidated.05/consolidated-00002-of-00022.pth b/mp8/consolidated.05/consolidated-00002-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..5dc199ed4bc2bd4fd0d25f06509e0d66006acf7a --- /dev/null +++ b/mp8/consolidated.05/consolidated-00002-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d523417042b266063760123a5400e4bb347d2b9b8de1d28e022c9805a5c6591 +size 4781917812 diff --git a/mp8/consolidated.05/consolidated-00003-of-00022.pth b/mp8/consolidated.05/consolidated-00003-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c7b41e68e99534fcfb0530b641a6c417d0448eb --- /dev/null +++ b/mp8/consolidated.05/consolidated-00003-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea93b4be783cdcffd63791ce92690c5c3652dad422f8531ae2ac23dadb9efb68 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00004-of-00022.pth b/mp8/consolidated.05/consolidated-00004-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..0a7815be0b4baccf7958370213d10d9cd6932326 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00004-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:680dcd11198bb77fb8b5a1175da3f69b4be2fc25a1cb2506ffcf1a6bbb299801 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00005-of-00022.pth b/mp8/consolidated.05/consolidated-00005-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..83f40cfb5cf6ebd8071d5750e548a92c87aceabb --- /dev/null +++ b/mp8/consolidated.05/consolidated-00005-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdbaf99c4f65266c91f6f261459b5f29d97a7110220364f330a35a152338140c +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00006-of-00022.pth b/mp8/consolidated.05/consolidated-00006-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e2b30a4a6de07e59d07f1059d44983467c6098b6 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00006-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc499adc5aff977d981612a4f39567a332bf097b335708990141c95c2b0f8238 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00007-of-00022.pth b/mp8/consolidated.05/consolidated-00007-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..bf1e6b5c065d3f82568983efff66ac45dd5839c3 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00007-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d96bdddfbcad2f54ff12a2c9d2d05255ca5360b90c81209f6b32cfde2c6781c +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00008-of-00022.pth b/mp8/consolidated.05/consolidated-00008-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..17a12c744f19f39528f46c93b8fb96cf12cbc582 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00008-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1fe6498d1cbe769659afa5f6c4bc2dcb9db5b88233d1b03a50dfb45c5972bc +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00009-of-00022.pth b/mp8/consolidated.05/consolidated-00009-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f220c22ad9348c8f5e695b68f36d765221ae72f --- /dev/null +++ b/mp8/consolidated.05/consolidated-00009-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb2031b4b1b51fd8850d602093170ec402d7a85e174282431ea838db5e27118 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00010-of-00022.pth b/mp8/consolidated.05/consolidated-00010-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..633caa0c317ff6b80e12689021db5c459f60cda7 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00010-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b722b5ebcb3aae7ece75bb231a7125208c51429e75418308e4ea89e469178fe +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00011-of-00022.pth b/mp8/consolidated.05/consolidated-00011-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a3109719665f18f2ddec74ffe22e7422d3cb33e --- /dev/null +++ b/mp8/consolidated.05/consolidated-00011-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786517e44ee9f80130790dc32f734c295afbe3723cf4526f3a1ef397aeebef54 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00012-of-00022.pth b/mp8/consolidated.05/consolidated-00012-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..6546e365214899b5cd4a957d6beb5eb82e833e26 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00012-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:642a084b477387abc4da36b2f8765bca277da1ab6d36019b11f008e557fe08b3 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00013-of-00022.pth b/mp8/consolidated.05/consolidated-00013-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..3064257eca4782c3e556bf7f1c358767f1911815 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00013-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8fb8f2aee3f0ba5ec94d0f105d767e9ad66d87537cdf8c8866702914b282d9 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00014-of-00022.pth b/mp8/consolidated.05/consolidated-00014-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c3ec0de5c59fcf0c9425aa419538461201d025a --- /dev/null +++ b/mp8/consolidated.05/consolidated-00014-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9377469cc1923e85b711d21ac26382fdd1cc449e09b195a3653f311e0a9777f1 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00015-of-00022.pth b/mp8/consolidated.05/consolidated-00015-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..0ff19d003112c36442d2d05dc43a09e7a1a848cb --- /dev/null +++ b/mp8/consolidated.05/consolidated-00015-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f773cec906dea226db111694443c763d68d77c5c08b65791cff5725b6c78a9 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00016-of-00022.pth b/mp8/consolidated.05/consolidated-00016-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..a581cdbb6cb6c3aea24202891aefb7ee8990cb5b --- /dev/null +++ b/mp8/consolidated.05/consolidated-00016-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77285633bec438352becadbf99ea002e05b383a02ab135f708bb5626aafd006d +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00017-of-00022.pth b/mp8/consolidated.05/consolidated-00017-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..0043ee7149452048665b6c6d1194b588664d88c4 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00017-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa60aa242c5ed3d9af633ec11ec9954fd01b4fbf52a24b9b4d615a6065a50eb0 +size 4781917876 diff --git a/mp8/consolidated.05/consolidated-00018-of-00022.pth b/mp8/consolidated.05/consolidated-00018-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3c413b67d0340b38226f074eea3621ececff465 --- /dev/null +++ b/mp8/consolidated.05/consolidated-00018-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87372c4eda3420e93a1bd10e3cc5375ff5e158e017d69222ada4d23912c2287e +size 4781917940 diff --git a/mp8/consolidated.05/consolidated-00019-of-00022.pth b/mp8/consolidated.05/consolidated-00019-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d0e590e7d5e29637f6ee3b0d46e0cadc1f90dbf --- /dev/null +++ b/mp8/consolidated.05/consolidated-00019-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135b8bf57ac1bf23093f25ac8a7afa378f4ce2086f1a6f494bbe079307b5facc +size 4781917940 diff --git a/mp8/consolidated.05/consolidated-00020-of-00022.pth b/mp8/consolidated.05/consolidated-00020-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..f0bbe368d6dd8552c77911933beb6664a8d271bc --- /dev/null +++ b/mp8/consolidated.05/consolidated-00020-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca6cd32f224209a619bf4901dfafec020fde03c00edc6f4f13bb1dde2e5b42d +size 4781917940 diff --git a/mp8/consolidated.05/consolidated-00021-of-00022.pth b/mp8/consolidated.05/consolidated-00021-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..bdf4fab2458e47b68a85b97e486b0193a89dc8ab --- /dev/null +++ b/mp8/consolidated.05/consolidated-00021-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ae57d1663e0793caee0b0f8c8a88c02b93c91a9ab9aa6ad7c6f86f6782f7f5 +size 4781917940 diff --git a/mp8/consolidated.05/consolidated-00022-of-00022.pth b/mp8/consolidated.05/consolidated-00022-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..dfe26486dff7d19ad530df6b1fd08c5a13b29e4f --- /dev/null +++ b/mp8/consolidated.05/consolidated-00022-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6460290d7b4a833e68e50b44879a5668d3c4772f26b3062cce994cb84b28e916 +size 961645392 diff --git a/mp8/consolidated.05/consolidated.pth.index.json b/mp8/consolidated.05/consolidated.pth.index.json new file mode 100644 index 0000000000000000000000000000000000000000..28b4564cf4f84c2b1efcd25219dd769b659fa5a6 --- /dev/null +++ b/mp8/consolidated.05/consolidated.pth.index.json @@ -0,0 +1,1144 @@ +{ + "metadata": { + "total_size": 101470601216 + }, + "weight_map": { + "tok_embeddings.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth", + "layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth", + "layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth", + "layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth", + "norm.weight": "consolidated-00022-of-00022.pth", + "output.weight": "consolidated-00022-of-00022.pth" + } +} \ No newline at end of file diff --git a/mp8/consolidated.06/consolidated-00001-of-00022.pth b/mp8/consolidated.06/consolidated-00001-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..f0c9fe3908ae85b7ef03948fd9a94b847741f846 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00001-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcc42cddc5dc31c2787c9d119749c9a590f0230ebe1c70459a293c0a289fa7cb +size 4870980313 diff --git a/mp8/consolidated.06/consolidated-00002-of-00022.pth b/mp8/consolidated.06/consolidated-00002-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e3bff8813581f8bab5abab910a64591fa75cf6f --- /dev/null +++ b/mp8/consolidated.06/consolidated-00002-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30a14b9f29b95c28dbe82051a978f1dbe27254f3c2b232b109df967674a48b7 +size 4781917812 diff --git a/mp8/consolidated.06/consolidated-00003-of-00022.pth b/mp8/consolidated.06/consolidated-00003-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f2db0b2d633cfaf6a563ac2182d5bd136de3227 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00003-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3785ecd6de7aad09511f9bfe4a3295234dddfe0db60bccce40943b6d7b33ff8d +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00004-of-00022.pth b/mp8/consolidated.06/consolidated-00004-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..a58b38620ba104e173ed075adad49148c5208528 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00004-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b98cd1f5d3c1fc4272ce7a4a03ed2f8fe01bdb478adfa599e644c3b8cc571c +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00005-of-00022.pth b/mp8/consolidated.06/consolidated-00005-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..80cbefdf931cb4ebdc15f730242e88a50aa5d50b --- /dev/null +++ b/mp8/consolidated.06/consolidated-00005-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec2cba125f927ff356ec159b6a0b0cc3909af0647dcdea4bed91d117936b5b7 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00006-of-00022.pth b/mp8/consolidated.06/consolidated-00006-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..993fccff2abb905ecdeb997a863618107d00fc75 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00006-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d0781200e4767828fc0e5068d115f36e72a59fafb2051dea6512bee4f3e56c +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00007-of-00022.pth b/mp8/consolidated.06/consolidated-00007-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..9fbddea56da0e7ffd67f373c1a2b0ea04d48b77b --- /dev/null +++ b/mp8/consolidated.06/consolidated-00007-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03771b8ae4d4f5dd154e9c0a9460ac02c299c413240c16ecfde6624c1f637ec6 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00008-of-00022.pth b/mp8/consolidated.06/consolidated-00008-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..0fd09cd27c88d12517be30dcbfca6c811553c933 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00008-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b00e15225694df5c1f20e62be8edcd93dc7127c5ad7b446a53a4e4a0251a05d9 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00009-of-00022.pth b/mp8/consolidated.06/consolidated-00009-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..55830ed6f39004a8d64e84e35538f46a278140db --- /dev/null +++ b/mp8/consolidated.06/consolidated-00009-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1260188226a2dc49845bfdae7f1fef1ab905a07d2be5b5725d1fa9f540968ce5 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00010-of-00022.pth b/mp8/consolidated.06/consolidated-00010-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..83729b4f40c79786105bed251ef8822dc6f81b7f --- /dev/null +++ b/mp8/consolidated.06/consolidated-00010-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea21c1cb5c00cff1f42b1befb326af220a01e5b4e296ab4158a85c530734541 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00011-of-00022.pth b/mp8/consolidated.06/consolidated-00011-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..c0f0f2fa67faf9339426ec8be6d93ee77a838c42 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00011-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3247515e4829973eebdea62630f11b786d285ba70293bfd14ad53dbe091c33c +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00012-of-00022.pth b/mp8/consolidated.06/consolidated-00012-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..37a1773e69c09eab997a4998b2b50e623cd9200f --- /dev/null +++ b/mp8/consolidated.06/consolidated-00012-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61cb1ac01bf1aa872551a1306e545144c7ff5cd5d7247db2d3c69dfd40cee05f +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00013-of-00022.pth b/mp8/consolidated.06/consolidated-00013-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee675da7f70e70ae6222b08c81d8948b7e712f13 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00013-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:178d16896ca127ea497617c7ea8c15300b490c1036e14c3dc325342ffbf4aa39 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00014-of-00022.pth b/mp8/consolidated.06/consolidated-00014-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..907d69fcd91e15432cfd7c90e852aeafa14ad885 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00014-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a2cfe6dea8d3d41641787d016b06e138fd5759ae93fa65063a745cfb5f2424 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00015-of-00022.pth b/mp8/consolidated.06/consolidated-00015-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d437b58a576288ad75f4ea2558447478ad14e14e --- /dev/null +++ b/mp8/consolidated.06/consolidated-00015-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85696140414c1c9b9eafb6138582be65d82194fe31de7781ec2e663bd722db2e +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00016-of-00022.pth b/mp8/consolidated.06/consolidated-00016-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..07be79213909c5c0884143ff5260d9ff961c0753 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00016-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0006aa7507e4c3172cadc6bc29df2cbdbf134da71d61ac10167ed6b2f92fa518 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00017-of-00022.pth b/mp8/consolidated.06/consolidated-00017-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..55d41d770e1fecff3b2dc9266aece6a63bfcd30f --- /dev/null +++ b/mp8/consolidated.06/consolidated-00017-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7cf72a5876c25f50f1b2a80c4d0bcfb1da2991bab298fe80a0721283114cb6 +size 4781917876 diff --git a/mp8/consolidated.06/consolidated-00018-of-00022.pth b/mp8/consolidated.06/consolidated-00018-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e49cb9c425802616da1734989cf941fd49794571 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00018-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773e2865a19f077bb031e6d43473d7c1ad7cdc41740eca5d7c8f2c3572394f1a +size 4781917940 diff --git a/mp8/consolidated.06/consolidated-00019-of-00022.pth b/mp8/consolidated.06/consolidated-00019-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..dabeed1433345066421a0397b5b37ee25208ec74 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00019-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb1646721da354c82aa74e15c0057d6a0e54ab5e42f098a0c2c49c0f3c1f24a1 +size 4781917940 diff --git a/mp8/consolidated.06/consolidated-00020-of-00022.pth b/mp8/consolidated.06/consolidated-00020-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6cad70fe4aae8811811f00ffa10ade3a0bd845f --- /dev/null +++ b/mp8/consolidated.06/consolidated-00020-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899c335e1f00e0e5dcfd5e63c11f6b83c6eff8a31865b54d5792c6b083a593a9 +size 4781917940 diff --git a/mp8/consolidated.06/consolidated-00021-of-00022.pth b/mp8/consolidated.06/consolidated-00021-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..28be4b4efedfc4b1ea4f19a370a039f652d29d0e --- /dev/null +++ b/mp8/consolidated.06/consolidated-00021-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f66c02e11979341fe6f155b755eb11ad5bc468f4a315f7bde64e995dfc73433 +size 4781917940 diff --git a/mp8/consolidated.06/consolidated-00022-of-00022.pth b/mp8/consolidated.06/consolidated-00022-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..14754ac32bc52dbabdfade3bc530feb56ff191e9 --- /dev/null +++ b/mp8/consolidated.06/consolidated-00022-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d20547c324f27ca207594d06e2220158a411513b12e193c4322e1a1f98b071 +size 961645392 diff --git a/mp8/consolidated.06/consolidated.pth.index.json b/mp8/consolidated.06/consolidated.pth.index.json new file mode 100644 index 0000000000000000000000000000000000000000..28b4564cf4f84c2b1efcd25219dd769b659fa5a6 --- /dev/null +++ b/mp8/consolidated.06/consolidated.pth.index.json @@ -0,0 +1,1144 @@ +{ + "metadata": { + "total_size": 101470601216 + }, + "weight_map": { + "tok_embeddings.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth", + "layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth", + "layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth", + "layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth", + "norm.weight": "consolidated-00022-of-00022.pth", + "output.weight": "consolidated-00022-of-00022.pth" + } +} \ No newline at end of file diff --git a/mp8/consolidated.07/consolidated-00001-of-00022.pth b/mp8/consolidated.07/consolidated-00001-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d04ea55d0175ced0ab1ede261137d77c3028758d --- /dev/null +++ b/mp8/consolidated.07/consolidated-00001-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8b35e51ff3c641bf58b0950d591daa5d7b8bea9b3f110a969104d519e00e9fb +size 4870980313 diff --git a/mp8/consolidated.07/consolidated-00002-of-00022.pth b/mp8/consolidated.07/consolidated-00002-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e4fae78be4ada2998aaf4d7e8cab66f43efb84a6 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00002-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:504a45c1ea28fdf5b564ccff2de88932b4472244fcbea4b01515ac71b5c9b6ec +size 4781917812 diff --git a/mp8/consolidated.07/consolidated-00003-of-00022.pth b/mp8/consolidated.07/consolidated-00003-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab52208a0b49fe19b1dfa218d1bf47044d64fbde --- /dev/null +++ b/mp8/consolidated.07/consolidated-00003-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:000a5c7a99ad5704225ce24989e74c5ec58723d682bcf5fe4ad160363905899f +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00004-of-00022.pth b/mp8/consolidated.07/consolidated-00004-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..e7191d1c18f999981ed5010f17d72d004031230a --- /dev/null +++ b/mp8/consolidated.07/consolidated-00004-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cba5597ffe5a3d9e88be32e1420b448f396c5e5301252d1f9ffed0eb05bf68f +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00005-of-00022.pth b/mp8/consolidated.07/consolidated-00005-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1724c8376f1aee09206496b8e8ed66c3c4cd072 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00005-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e86ce3cc9620f43ae7d980d14cc6c64049ee05dbf76d0c5f500c226289968a9 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00006-of-00022.pth b/mp8/consolidated.07/consolidated-00006-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f736014b23b98936164e52d49410cb3c7e7d76b --- /dev/null +++ b/mp8/consolidated.07/consolidated-00006-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d27045903789b0ef942921e30de305ba95cd9065a519ca8a73ef3104df085be4 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00007-of-00022.pth b/mp8/consolidated.07/consolidated-00007-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..852aa2a0a0485bce70e40aee2652d4350d5e40c5 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00007-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d9fb749e6869709999870caba1dc7e0d099c6c226fbe0827a66cd43cb84658 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00008-of-00022.pth b/mp8/consolidated.07/consolidated-00008-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..49664d74a9fc85523cf10aa2180a1e6cc7b70bb1 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00008-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a27476dbb07fe9a6b9b085fd174aa7737d26c6db0efb8d16e4bf28c1a6c6cb +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00009-of-00022.pth b/mp8/consolidated.07/consolidated-00009-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..4dba518c226229aa589ccdf7f936c998516a5c6d --- /dev/null +++ b/mp8/consolidated.07/consolidated-00009-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:253ac45bc8a5e00d1804874a8d90da60cab4959d9fbe44c46830aa8e744a9df0 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00010-of-00022.pth b/mp8/consolidated.07/consolidated-00010-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce4cb8d7405569223b7431464f3bd2a80b2001e3 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00010-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c1a199cb57604217bfab885d2fac425483c7bfbd20593ea8307c7a77cebc63 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00011-of-00022.pth b/mp8/consolidated.07/consolidated-00011-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..64686bb1eeb34eef3fc4db04a2a308f28cb1b2df --- /dev/null +++ b/mp8/consolidated.07/consolidated-00011-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b971257c2384b1e5ff7bec1965c96374ec8a739e2e7f65c8b248eb59d26cca6 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00012-of-00022.pth b/mp8/consolidated.07/consolidated-00012-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..02d697b8dbcd60582e6aa1a13d9a84762e067c3a --- /dev/null +++ b/mp8/consolidated.07/consolidated-00012-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfac07d79d03bb8912ba37cc84ae70a326330ed506907f633c2e8b97a918a026 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00013-of-00022.pth b/mp8/consolidated.07/consolidated-00013-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..4af51d15684cc8b18bb49c6b9ccbf662e1f1a948 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00013-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08edba85f23be5d47352a3a334535dff02019c248c220983ebfbc15cbaafda5a +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00014-of-00022.pth b/mp8/consolidated.07/consolidated-00014-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..dd73eeeca59847346b8e4740d346b471f1eb660a --- /dev/null +++ b/mp8/consolidated.07/consolidated-00014-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238364a646e97ccb4c1492a5d4bf63d229652d703aad73d1f99b6f9a220995a8 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00015-of-00022.pth b/mp8/consolidated.07/consolidated-00015-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..08523853d25ba1ed1688b443ade9ec22ac902bee --- /dev/null +++ b/mp8/consolidated.07/consolidated-00015-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f12dc73655c21508c674bf92191027bb2fbd9aeb4358f365c9d2a1b33eaf8ba +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00016-of-00022.pth b/mp8/consolidated.07/consolidated-00016-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..9236b26a86ef3f8f92e41e233853738917193573 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00016-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c11d95d38bcf53b4fc6307d712736af55b7cb6e1b87fc9155ee5e80ab39fcd90 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00017-of-00022.pth b/mp8/consolidated.07/consolidated-00017-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..de789517ee45c87f37f32251c56d01bcfba3e894 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00017-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4892e5392e3eb7a9ab082ff50dc800b59444adc392be3ab3d9ca742ab16bd3 +size 4781917876 diff --git a/mp8/consolidated.07/consolidated-00018-of-00022.pth b/mp8/consolidated.07/consolidated-00018-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..2fa90034ac6a2455ffb2821a8c40c17c370c7676 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00018-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:590b88d3dbf06f1d36eddbe6b741d2b3df5300ca975eae0224cea5fccfca4bd0 +size 4781917940 diff --git a/mp8/consolidated.07/consolidated-00019-of-00022.pth b/mp8/consolidated.07/consolidated-00019-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3a0c948ec87e694556fe4cad4c7351e56dbfb14 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00019-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9420fb6cc899a393477f51479bb4018b388abc1f5bec0c9fe19e5fd883cec87c +size 4781917940 diff --git a/mp8/consolidated.07/consolidated-00020-of-00022.pth b/mp8/consolidated.07/consolidated-00020-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..928c850924200b8ee78856e5fd6540336285335a --- /dev/null +++ b/mp8/consolidated.07/consolidated-00020-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:981f57f96a236d8645d8f8112699a51c1890e57574b20fadc44f0425cc766360 +size 4781917940 diff --git a/mp8/consolidated.07/consolidated-00021-of-00022.pth b/mp8/consolidated.07/consolidated-00021-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..94504d16e80e5a90f89a7f3befdfbf6162bdfc89 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00021-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d210051e575c6192d52af787884de2cf3d548ed1db5c8ba62651f448cf2a496 +size 4781917940 diff --git a/mp8/consolidated.07/consolidated-00022-of-00022.pth b/mp8/consolidated.07/consolidated-00022-of-00022.pth new file mode 100644 index 0000000000000000000000000000000000000000..8ae05ac20425c1e0a661369c845a2f67f4cec607 --- /dev/null +++ b/mp8/consolidated.07/consolidated-00022-of-00022.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b45a8a960532e4ba5f19c1452a96b75537e29607533b06c71fccf7bcdedd7b +size 961645392 diff --git a/mp8/consolidated.07/consolidated.pth.index.json b/mp8/consolidated.07/consolidated.pth.index.json new file mode 100644 index 0000000000000000000000000000000000000000..28b4564cf4f84c2b1efcd25219dd769b659fa5a6 --- /dev/null +++ b/mp8/consolidated.07/consolidated.pth.index.json @@ -0,0 +1,1144 @@ +{ + "metadata": { + "total_size": 101470601216 + }, + "weight_map": { + "tok_embeddings.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth", + "layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth", + "layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth", + "layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth", + "layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth", + "layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth", + "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth", + "layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth", + "layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth", + "layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth", + "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth", + "layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth", + "layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth", + "layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth", + "layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth", + "layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth", + "layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth", + "layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth", + "layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth", + "layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth", + "layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth", + "layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth", + "layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth", + "layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth", + "layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth", + "layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth", + "layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth", + "layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth", + "layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth", + "layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth", + "layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth", + "layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth", + "layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth", + "layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth", + "layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth", + "layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth", + "layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth", + "layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth", + "layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth", + "layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth", + "layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth", + "layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth", + "layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth", + "layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth", + "layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth", + "layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth", + "layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth", + "layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth", + "layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth", + "layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth", + "layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth", + "layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth", + "layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth", + "layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth", + "layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth", + "layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth", + "layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth", + "layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth", + "layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth", + "layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth", + "layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth", + "layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth", + "layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth", + "layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth", + "layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth", + "layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth", + "layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth", + "layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth", + "layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth", + "layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth", + "layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth", + "layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth", + "layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth", + "layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth", + "layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth", + "layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth", + "layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth", + "layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth", + "layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth", + "layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth", + "layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth", + "layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth", + "layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth", + "layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth", + "layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth", + "layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth", + "layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth", + "layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth", + "layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth", + "layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth", + "layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth", + "layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth", + "layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth", + "layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth", + "layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth", + "layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth", + "layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth", + "layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth", + "layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth", + "layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth", + "layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth", + "layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth", + "layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth", + "layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth", + "layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth", + "layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth", + "layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth", + "layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth", + "layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth", + "norm.weight": "consolidated-00022-of-00022.pth", + "output.weight": "consolidated-00022-of-00022.pth" + } +} \ No newline at end of file diff --git a/mp8/params.json b/mp8/params.json new file mode 100644 index 0000000000000000000000000000000000000000..33a7472fca2dc52a6ce56f0aceb7a8ff07659bfb --- /dev/null +++ b/mp8/params.json @@ -0,0 +1 @@ +{"dim": 16384, "n_layers": 126, "n_heads": 128, "n_kv_heads": 8, "vocab_size": 128256, "ffn_dim_multiplier": 1.2, "multiple_of": 4096, "norm_eps": 1e-05, "rope_theta": 500000.0, "use_scaled_rope": true} \ No newline at end of file diff --git a/mp8/tokenizer.model b/mp8/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..a097ce5a06fce0fa3d685a8cfb175cef243dfde9 --- /dev/null +++ b/mp8/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e9d31979e92ab929cd544440f129d9ecd797b69e327f80f17e1c50d5551b55 +size 2183982