diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/mlc-chat-config.json b/mlc-chat-config.json new file mode 100644 index 0000000000000000000000000000000000000000..f5c4693c65249787fc2c8125cd6d88227776dbd2 --- /dev/null +++ b/mlc-chat-config.json @@ -0,0 +1,86 @@ +{ + "version": "0.1.0", + "model_type": "gemma2", + "quantization": "q0f16", + "model_config": { + "hidden_size": 2304, + "intermediate_size": 9216, + "attention_bias": false, + "num_attention_heads": 8, + "num_key_value_heads": 4, + "head_dim": 256, + "num_hidden_layers": 26, + "rms_norm_eps": 1e-06, + "vocab_size": 256000, + "hidden_activation": "gelu_pytorch_tanh", + "position_embedding_base": 10000.0, + "context_window_size": 4096, + "prefill_chunk_size": 2048, + "tensor_parallel_shards": 1, + "max_batch_size": 80, + "attn_logit_softcapping": 50.0, + "final_logit_softcapping": 30.0, + "query_pre_attn_scalar": 256, + "sliding_window": 4096 + }, + "vocab_size": 256000, + "context_window_size": 4096, + "sliding_window_size": -1, + "prefill_chunk_size": 2048, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "temperature": 1.0, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.0, + "top_p": 1.0, + "tokenizer_files": [ + "tokenizer.model", + "tokenizer.json", + "tokenizer_config.json" + ], + "tokenizer_info": { + "token_postproc_method": "byte_fallback", + "prepend_space_in_encode": false, + "strip_space_in_decode": false + }, + "conv_template": { + "name": "gemma_instruction", + "system_template": "{system_message}", + "system_message": "", + "system_prefix_token_ids": [ + 2 + ], + "add_role_after_system_message": true, + "roles": { + "user": "user", + "assistant": "model" + }, + "role_templates": { + "user": "{user_message}", + "assistant": "{assistant_message}", + "tool": "{tool_message}" + }, + "messages": [], + "seps": [ + "\n" + ], + "role_content_sep": "\n", + "role_empty_sep": "\n", + "stop_str": [ + "" + ], + "stop_token_ids": [ + 1, + 107 + ], + "function_string": "", + "use_function_calling": false + }, + "pad_token_id": 0, + "bos_token_id": 2, + "eos_token_id": [ + 1, + 107 + ] +} \ No newline at end of file diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..00e904f29b183b8c66ba6f36be4dbf9575c7418f --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,2854 @@ +{ + "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" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..9bf65226f50d2f5e58780571c80a2408d7d6dd02 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a9d30707e659e2e673656d71f5aef7a9fb9fd83bb9a77558dfc5abbe218a05 +size 1179648000 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed896c0c66d5b36ff2d98318ec1ac3b16e931011 --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51eb4d962189e945a84e94e0dc1aad3f8f90cc1a11e18029670afcd0ea0acb1b +size 42467328 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..b969ff91cdefb3e37969efa9e0b7a42d86710dbd --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b86902f4e36868421e5228b9445051f8290b292df22a6d1af836dcecc1f25c3 +size 42467328 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c89eb59e719f1443ec2e32764dc448a48bebdfd --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ddf38a72fa5caafb544ac458fb82ea9911a0c04a4144560c26052d5ffd6729b +size 84934656 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..17a65b09ec861d3b3c5618b2ce2264995d8fd223 --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:729bd9b0aeb21c20ed7e158d6257ac6689bbe202bc989423ac0ccc655eb1cd8a +size 28329984 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..b70fe6875677f9fa56ce36f9bfb808fdaf75d404 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:578f39f8f9fc2f09138afc884a952d7cc3a9a31de4216acd10e88e19e0b75f8c +size 42467328 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..604f256d2561877e876281b0d4b76f37d1602be2 --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7160079ce3edf07e98fb2fc1e341e00833f17297df013bd33949d4c9cfbbc537 +size 84934656 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..b7631fa5c9b2404afa1417192a569d448c5a91bd --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c0cdccf78c75753be8d382f127bd2a83cd3f6f4052457a941a10ca163e0b99 +size 28329984 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f5d0551c3f9b2501556fc3a54bf50e33f2f9aa0 --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5514e0c8e7b3ed1cbcc1605eb5be1733b6ab3514cf8a0508fc72f7d05ed8bcb +size 42467328 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..9c5d767f69407bc3ca91934b75b09d03976c3b29 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78dd6aa0956e528bd824a0c1c66d1f83c22b57923650bd4dd09a77e20fff13dd +size 84934656 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..525e7d260e30066fc475ea9ac570e68c7461c6de --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1e49052aaac05e170b32164631be481bf7f545bfd971a127c43cfb65b0b49e +size 28329984 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d6256ec3715c16dcb3ac7bc2b52a6a27968b48e --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29960965b384ae5ab3d898a4dbaa8fddd28fa0e477ac28bcac49dec12a5ac67 +size 42467328 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..91ca294afbc569839e9fcdf0624efb1e49731347 --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b860ae6eb64c9ff97f4a4f0827ae4004da7d1db7ea6b5113bb9000f8966142aa +size 84934656 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..e5fd29a53eb59fcc09a73bc3e39f96d1cfca240d --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfaaee1a95354241b3d0ee19b6c2ff83d159e5381a541f842c897404120ef0e5 +size 84934656 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..e0073bdab65040addf85aa6052cec46e5f3233d0 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d1cd33738b0e058dd30136025f5e6e038b5f68cd7f755900d74cc9eaccd197 +size 28329984 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..834668b250c2a45f007e395edf5feaf040121cc9 --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc1f97a65dde6fa2c1e5397afb612266944b343f2eaa868b635ddd25829f8a42 +size 42467328 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..92a3b5bdd82d26c5f0c47457c79483916e399b78 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee7f3e807e071f87059fada1bf3c52ea1ee164a3de3bf03a69b2f60f2cb9eadb +size 84934656 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..8618616cbc23914280435f5febae6cb2a6895d3c --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2862ddc67ee91737032cc23defd79e554f3959b495a3448d3b23242755f08adc +size 28329984 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f0259fe0fe85c10afa559def80a4a1f32d6dfe5 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1c813eb5e7da3d6194569d6cb21602fc6eff2dc8e1b0eb753f2d5df148189c +size 42467328 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..c37bdb7ddbb565c35268451957bc22d473fc4995 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d90e644138b0e76f1fd37059fcaad2fd7906a56c37d414e645bc1e18c927ce +size 84934656 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..89e3b0a2b16ab7556b36762bef65a83fe2f95663 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc17063d5daf5299e2ce360b7f60855d6016af1dda2154db8c55201d1a9ab955 +size 28329984 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b491189734b109bd92215641606bcda6f156f06 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ff9a7cccaa3776434a9d895aae4fb5c36c736bf2ec98784226b4c234940fbb0 +size 42467328 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..855c5093aa8fa82f888325c1a51df96e1a01d034 --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7f9eead173e1da3a7f8b33c245618d2fbd6ec0a899f0042ffa1b2d3e965330 +size 84934656 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..c50a8a5e76d71cf17759d78c1fa8f78f874fc5d1 --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f30763a8bbbcaea609a0087ed75fadb5e771c06378dd2cea94cf17e492e8cf +size 42467328 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..68ca8db5e77379ede3d0ec34931e7fe8b422b11b --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:778078026e97540cfb252443bcd187498460ac184abb723536b9968205b63775 +size 28329984 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..c427220ecb4c173b14ed9fe908a2bd270dfb83b5 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9d09b13a33525e14bdaee6efc65c551ac7cf7680e534b940ab122a3a7c1ac9 +size 42467328 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..126ab160b09ea05f193b1a6b09e2ec8ac3b79a3e --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fff8053b595fe88109bda0af664ada2247db59e66b17955a1bf6000ddf8ddd7a +size 84934656 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..833fd9086c4cd52e3e3a7b0b28b8e11f1380920e --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf88756bc62968b1bc9a6df58c9a690fbd04fff68e8a0a73692af51cdb929001 +size 28329984 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..22ceeac194871dcc901119631b7c2e4cd3c22018 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7f2d7827ee01c2dd41401c7b3b1700ad3a4ff620e8bb734f92630d342dcc7f +size 42467328 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..6650a159906ae7d6bdf0d2e780ecc80a74486c8e --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6728cd9d15f8317b5d2f531e8c9880a0700bf105dbe508cd53b63528f0bf638 +size 84934656 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..04f4c57f7c5f4332988d2dd64bfc6dc3a6011859 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05df72ab189498465949abc5b018e61df06db1933a95a9e6f067a7856d0676a8 +size 28329984 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..523858d4357cf65e9e3597cb448fa51526da36a2 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea204fd04e0d2fc728a9861a459216bbfec629c152004ba625f52cd8837bd51e +size 42467328 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce320e44ef5405479ff151d734e12dc182ba420b --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4944be99943438af00e1591faf33affd3c60b4004c8316ef7a3c539283cb26d +size 84934656 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..cef133fba06a3287be30b6307616e3d3dc30def5 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efcaad0057bbea1479562622b205be7919205eff51f3d7a73ea8745a1a83b45f +size 28329984 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..4ff152e7c85708f396b39f575769e035915dd722 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d1f8d138a69ae44e339b0098c094917a7bc7e250d101135640ab7aac609ecb +size 84934656 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..f85d1aa58185281bd2c70937c7e956a0594e4f8e --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97efb608ac44cc804198faec3ee66eafe56ced6b7ca5359700c6f1df75b7205e +size 42467328 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce4e4c825c8151549bc2e95211ae44c09503c16e --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:accc13d34cbe37cbe6563161fb90470b5d376e8d7d3650980b1a10cec2bbf9d4 +size 84934656 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd6ccdc417082b231aa458017f0c1dd267f36021 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61be0d51fd43724e4b270a79901549bb4c23b7269ba099fbc0d0fd813633e99d +size 28329984 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..8edd6fb3da4a09c4995188407b9e2fc891f68053 --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd106556fb721b1c28ae3f4026bc83eb1b08ed910f2ba5f466c6b5f327d91cb +size 42467328 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..39d3462e2214d8d27b25f00b54d7dc03c41b11d3 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df30196f56b19a5bce54a9510d8eca6157457436bc4fa5a7057ff284daeee452 +size 84934656 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..f4047655f086bcb94a858c62b16f37794cb5eda8 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d573c85277a481c98e513525d32fe77a1cea04d1dbe3fba2231f42c24d0399 +size 28329984 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..aa6fdf1a29a5bef06908804e469d3a8960489ab3 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00cb8939f03e5817d6d412de8cf2c923c9568d5493e382cec7faf5718fb034eb +size 42467328 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..26bc0df3720b95e8cad5c73a19dd212aef29ee8d --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d60bee8a526a133c83f6a8dd7b618dcb2cd0dc3dc95ce6ff1289646fc11479 +size 84934656 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..7fe39cbe22d60a146a80811aa4fc5230fdb53697 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f6c55eee3b0cb0cb3974a8736926b5810e5189536f21afbf81d9676bb418b0 +size 28329984 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc4ff465a67754af610945c1ad2a20f3dd2a637e --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cf547eccb1b82aa64f208cee9682d7f558ca84e0aead7d9d3d1420d90f3d992 +size 42467328 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..620ba027750726739ae3180909e99acd66660ccd --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373acf6cd141e5f31e1b1509866c88a5acf91f22bd66f3ee787b33c1882cfe8a +size 18874368 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..4556e56f31fe03d3bd8901ca1b690bc7419de838 --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb7a7ebded7dee460b85b3f84ae4d210b05aacac9313320e36c57c39f5994f8 +size 84934656 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..61169a114dbdad4235600c27e12b2171dbcfcfb5 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73cd57dc6213c3366140d5c5ef03c1c5e0f0e14619157fd42dedc03927e40527 +size 28329984 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..930e5dc3eba867ba4ddea33a6561cb7238bac64a --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48b60bc429aaf6dfc3b8c9cb0e2e4262c2c3d12c24032eb8d5867544df073f42 +size 84934656 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..d244f9ef7b0a2dd37884ac0a3cd95e39e90d4b1e --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd867a63518b53cc69e851ef5aa440ff25b9809d21fda35d53de193961ff6d1 +size 28311552 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac182900f105fb1266725c9a909aac87139f2bfa --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0188ba50d8228805982029c277fc0e87aa57473b8363037c648f6d006ff828a +size 42467328 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..bfafadd27dd968474be69c2ddffde280df9b1173 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc885b7e34e180cb057e94359a7c1960da9f747bda589d749cf57e2103a1a49 +size 84934656 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..2af3626ed6586d9bbce0e9d59ddc2a10d31256a1 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c18fc013cd212dd8b78c40b046fc6d2abcfa626f983d52890beca7b606d2d54b +size 28329984 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..cd89dea43eae3cb20f1a5bb9f520719a09459145 --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30334ffc59ce343cf2a1b973174acb7722823463adc07e19a99bd0f404bc9906 +size 42467328 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..c6597e3128bba6c66023da1f29cb929e6f4cb427 --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62e1aae53eb3f22e25e00d1af4d200c583dc1b3b90bc7ee34feb0066a6b52b3 +size 84934656 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a94ee606bbb1e8871e29931ebc823015a6d031a --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4385fba9cbe54198e7b6510654e79834355c3c294564ca7498084d9b2ebd8712 +size 28329984 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..e40a707c54492c0fc1a5644639e396a49dbfeac2 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0737dbbd2b60c04d27f228529c5ea930d1979a9aa80752b08df0017307680c34 +size 28348416 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..819081ceac0670b578c5c1e0dad1ea70c97e3f29 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63e53541d34197720c06f297aa8142ac6b6eec002c7987b296f26e8b1400f931 +size 42467328 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..6503d0f15d995de9dd0173427674594acb5f5bd9 --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfe4376470177a821ec8c015cf1eac0a7a2dee3864307ccccc099625e9da468 +size 84934656 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..9997418e0c0f46b28ba89911cff82dc7cf3e847f --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e34494b886032f529df7727f5dfc6dd6384cc17f7315cd0da96f1a901f0d868 +size 28329984 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..c31ef2adcda5ccb815def9f76aab274ebe6f9a09 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582247fb3c2bf687cbe9413fe18d18ad47bef4b65df7d78905e10335c6134764 +size 42467328 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..e73eed846d834703d0d6204afbcf34a12f95294d --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46e435d1e326c58e145309f095395274ea5b2e59b4059527e5cc08de5ab8e89 +size 84934656 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..15e92f0be8997524a4cd0a65c23e76e68da28c87 --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d88f80a7956e303cbb682b9a1866fcb73958d4aac00e25772e152825e078a5b1 +size 28329984 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..ee53f337e5c59fd357deb66b0c10d09af5414c00 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ba8fb57208805ef1dc23cd7c86e9a2d1fb7c52c3940d292cd5bb2eb24b3fac +size 42467328 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..f761885c0e2afe202ef3d97e4ef179b8a90160fe --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f267befc88c3f7092eabb6000a03ecf46d6ef056726643b943e16f19af5fd8e +size 84934656 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..963db80728ec499f48a972ff824060da1651761a --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dd61d48167546391f370d40c2ded0ce0d44fd28571d34d37959130e352451f0 +size 28329984 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..479b673eb59f6556cf848c252b0e496f8d65434e --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1164a2578a7f87ed99c2bbc76c5dfbbbc6a1a803605391acc3f320fc989ffd7 +size 42467328 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a19dd7801c8da13f93346a79f8d9f05fd970d26 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcebc04219f8081a5f483e58103c0ddbbbc631a0a54fd6dd9d55778e041f70ee +size 42467328 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..f32e01bfe71aabe9c804293a1df952de10d1a882 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b14c02df872072ba9f987d94536ca6b8d7cb4bc2013ade9825433409f337b329 +size 84934656 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec855c0aca0321eb3722e053c4e210a1fce4f169 --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df4cbb7772729ae423d82561bbd83e4f13e9da40c78da636849c7c32008e919 +size 28329984 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..75b491d98d7f306956041c6d2ac65a52cf77a9a7 --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a426f81210f03d6ad53277416e1fdcdf37d8065e4817613edaf6c67a343426be +size 42467328 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b307ccec3dc103d1fd3bcd8bcf6a8833e9e4d47 --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba42e84be63ce4a018375f311c9584968319d949678286d2293b0bbab404ff39 +size 84934656 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b908d750c8f110e69e8e9dd537647deeaab705d --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae5f15ec67e9e62334d205ebb01b8aa89f39928f26e5bb425aa2a666f210bd14 +size 28329984 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..441817c7fd0739195e9779fd065f579d14f3cd69 --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c6351e3162626b276f524a57836144625c2556dbe321b57cbd8fd486a68fab +size 42467328 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..d6bcc15e2029955c08f19ddae8e072b7fd1a146c --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c08d4dc8412b19fdc870c164b83c341b236ec6fe7bb4a9bcfe0dc100faa20286 +size 42467328 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..64ebdc7adeab73bb53e07bb4b8324e9b0e07ef59 --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1deaa79b99fc12a08951433156585532ae44480a8d6168695bb2f5e217f08829 +size 84934656 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..5b9f36ff2fc3e5bee84e1d42c9aa771ab7aa3793 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5100d59715e48a1707428000c693addad647312320927e16a25d49713e8480f2 +size 28348416 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..3da19e404cb2d5001af838d77962efb2dadbe974 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280d1e86220713afb8b8422ed76d038826c5d96560805ba461b4aa19f1e4897a +size 9441792 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..97de21f94a1e66ef68e62a63c787922747d95442 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc924d6c421c6113cb44951d2db19c62d1763f3c3b6281aac8e08dd7b73a281f +size 84934656 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..30bb7747e554d2c0c6561c2afcab6211bea251fd --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2976f86c71e8432378c593e69d5b5f9fd91052fb39fe0076f06776ef985a6f +size 28329984 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..87df8b34caa7086990087d64a0ceeb4d047cd714 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2009 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}