{ "metadata": { "ParamSize": 210, "ParamBytes": 5228683776.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 1179648000, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 256000, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1179648000, "byteOffset": 0 } ], "md5sum": "bd04f657e68800e39b6f5f375441ab1c" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "3cd51ffed8bfd0b4138d1aeead787cea" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "a05426adc350ec2c79e4bc61d70d60c1" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "01352f4651a8dae405b56910978034a7" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "1ba6e5b23e2819379762052538555e2d" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "ac52e6fa05a81436cc20a682bb31b01a" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28348416, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 4608 }, { "name": "model.layers.0.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9216 }, { "name": "model.layers.0.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 13824 }, { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 18432 }, { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 18892800 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 28329984 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 28334592 }, { "name": "model.layers.1.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 28339200 }, { "name": "model.layers.1.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 28343808 } ], "md5sum": "4baeb6ab99e46e08140f6d42a10a136f" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "787dba4e17c4fd4357f74e69460c84d8" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "9bee35a6635351a555004148477e8249" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.10.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.10.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.10.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "730e18cf91d7e7c6e816f531e1cfeff0" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "746c0be2b6d8d216f1517570a9efb57c" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "eff43f58197bd73031284872a1dd7d43" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.11.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.11.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.11.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "ad9b697ac38b21dd5d2d094049c4bbf9" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "78594a4d8730c0de2807d79fb405e372" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "71d536b6a9847882d6a817079cf5716b" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.12.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.12.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.12.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "11cba9275957c38808a9b64c73b91173" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "0c38d06e0b70989cc822af58a3df50bb" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "cb315422a8dfee20be4509c388d28df5" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.13.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.13.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.13.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "530323712e97e229aaa29629e8547567" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "6875b5e39164f5eb0a3bead2f713e01b" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "4cbb3e84e9b7d6be729bc2cb34e38827" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.14.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.14.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.14.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "69932e69b4d572540147fb8d8daa52ea" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "ab6f22a124667f8c39b09023ebee129e" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "97d2d3288acada5a59e0e8796bedf659" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.15.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.15.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.15.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "fa7092621e9e1bc30c07c2e2d84c4d2d" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "8ca17fd3bd99a1b2f12030b5839695b4" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "79d58166414da574f561ba51e86f2fd7" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.16.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.16.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.16.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "7e13eeae220123e0c1f3e9d843255485" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "22e316ebb372e29f220796afdcd2ee90" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "656dc7f41628463c8bfae102a733637b" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.17.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.17.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.17.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "7717c1fb244f18ff11567ce399f43672" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "e689ecedbbd305c990a890ba7a512f3f" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "d3b3716b7ebcf5cba77aab9b2626a8c5" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.18.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.18.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.18.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "841c546d5ae8142476b339d199bb3b8f" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "726fd1886383ab5cf39ad8eed73c7877" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "f7be1bd0e675520d79c615ccffff940b" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.19.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.19.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.19.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "73c1238e23a0631ea0448ccfa3f0b711" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "87df5c0eba26b631961c2dd5996904ac" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "7abb06539525d99d286f23f2510a6a15" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.2.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.2.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "8b3f6503f497847b70bef7b8fdcec329" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "8a6d2c22089f5697a6cf7ceac805ecb9" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "76ab3741b10d638ffb2cbd0385f5c726" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.20.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.20.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.20.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "be881a12c18c80ccf6543bc1abe3aa0e" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "8719df36a1f011f693a6f34addd7cdad" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "3c5634e209687d6a6366acc5fe9429f4" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.21.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.21.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.21.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "91877a5e7f27b0fb59bd8d0920a7b4bb" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "9934f4c2b69a4091dc3861bcfb836a2f" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "3ec6e7ec45fa16cf40c46036c1719c1f" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.22.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.22.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.22.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "640babc79070007be0aa91cdd22a80cf" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "446558eee16932ce64b00d7591b2ea79" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "029005c06e461193cabd99d94578f76a" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.23.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.23.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.23.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "f10d50ea8b06958a6179cdad2bfe63f1" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "ce18a53950c7a65819790ac40f331460" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 28311552, "records": [ { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9437184 } ], "md5sum": "74a0b41986d05bcf56b5b848b2540032" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "1fa8a2ad0ac76df5408405c499185019" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "33157e305be4722b41078fb1e886437a" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.24.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.3.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.3.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "7dc6a94ae1e14a228cc4f529f3721f73" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "ebf0dffa00892d933edbdfd9ccb4a7d9" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "e056b67a5781c92a0ddc6609770c93a6" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.4.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.4.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "bc00e8fb6d0ea2f03defa30fb0c0f1cf" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "5fca07b60463941528c09b6ba6e78c5d" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "0693937fe395959db6116fb3bf0714d4" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.5.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.5.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.5.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "09a7c0a5c60b343993bbc19a564cd35b" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "75d6548187e3bf06464b603fca7ec22e" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "a444e56b6147a9658bd9b27f2dce58ff" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.6.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.6.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.6.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "1eab15611ac12561bdee2869ce01cd04" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "cd255cc3726f542b8ab8791b02b951af" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "9282b473f3de1d9729d9649d6fac10ee" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.7.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.7.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.7.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "20cd72177436a84015feb09ada96beb9" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "c2ddb40da3ce09337472d346b81f1b1f" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "90369159e754aa884ceafe344d5c651b" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.8.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.8.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.8.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "e8277fa029e6bf6a5d7a3b54ea17faef" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "fd7ba589c0c05f01cf741093a6a8ad87" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "6deb54d82c855a1df96e50051743bc86" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 28329984, "records": [ { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.9.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.9.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.9.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9455616 } ], "md5sum": "ae01dc53fec55e10cff4c54c7cb5fbf8" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.24.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "e62d5779311e4b1e79d5542e97bf9215" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 42467328, "records": [ { "name": "model.layers.25.mlp.down_proj.weight", "shape": [ 2304, 9216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 42467328, "byteOffset": 0 } ], "md5sum": "dadde1e874a9f29f03da804b70baebd7" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 84934656, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.weight", "shape": [ 18432, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 84934656, "byteOffset": 0 } ], "md5sum": "8d88737e379b8e2a75e9d3140c54bf60" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 28348416, "records": [ { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9441792 }, { "name": "model.layers.24.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9446400 }, { "name": "model.layers.24.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9451008 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9455616 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9460224 }, { "name": "model.layers.25.post_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9464832 }, { "name": "model.layers.25.pre_feedforward_layernorm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9469440 }, { "name": "model.layers.25.self_attn.qkv_proj.weight", "shape": [ 4096, 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 9474048 } ], "md5sum": "811a932b1be1b38f1095c9e505a59ff1" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 9441792, "records": [ { "name": "model.layers.25.self_attn.o_proj.weight", "shape": [ 2304, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9437184, "byteOffset": 0 }, { "name": "model.norm.weight", "shape": [ 2304 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4608, "byteOffset": 9437184 } ], "md5sum": "cf0010eca37346feab454f386195a617" } ] }