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..9e4fb9b4633366d55ad0e5bc761312124bd9864d --- /dev/null +++ b/mlc-chat-config.json @@ -0,0 +1,78 @@ +{ + "version": "0.1.0", + "model_type": "cohere", + "quantization": "q4f16_1", + "model_config": { + "model_type": "cohere", + "hidden_size": 8192, + "vocab_size": 256000, + "num_hidden_layers": 40, + "num_attention_heads": 64, + "num_key_value_heads": 8, + "intermediate_size": 24576, + "layer_norm_eps": 1e-05, + "position_embedding_base": 4000000, + "context_window_size": 131072, + "prefill_chunk_size": 2048, + "head_dim": 128, + "tensor_parallel_shards": 1, + "max_batch_size": 80 + }, + "vocab_size": 256000, + "context_window_size": 131072, + "sliding_window_size": -1, + "prefill_chunk_size": 2048, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "pipeline_parallel_stages": 1, + "temperature": 1.0, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.0, + "top_p": 1.0, + "tokenizer_files": [ + "tokenizer.json", + "tokenizer_config.json" + ], + "tokenizer_info": { + "token_postproc_method": "byte_level", + "prepend_space_in_encode": false, + "strip_space_in_decode": false + }, + "conv_template": { + "name": "aya-23", + "system_template": "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{system_message}<|END_OF_TURN_TOKEN|>", + "system_message": "You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses.", + "system_prefix_token_ids": [ + 5 + ], + "add_role_after_system_message": true, + "roles": { + "user": "<|START_OF_TURN_TOKEN|><|USER_TOKEN|>", + "assistant": "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" + }, + "role_templates": { + "user": "{user_message}", + "assistant": "{assistant_message}", + "tool": "{tool_message}" + }, + "messages": [], + "seps": [ + "<|END_OF_TURN_TOKEN|>" + ], + "role_content_sep": "", + "role_empty_sep": "", + "stop_str": [ + "<|END_OF_TURN_TOKEN|>" + ], + "stop_token_ids": [ + 6, + 255001 + ], + "function_string": "", + "use_function_calling": false + }, + "pad_token_id": 0, + "bos_token_id": 5, + "eos_token_id": 255001 +} \ No newline at end of file diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..f085b9e68cc0a41b541a93e98d127871134e1976 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,7049 @@ +{ + "metadata": { + "ParamSize": 443, + "ParamBytes": 18167250944.0, + "BitsPerParam": 4.500119595955907 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 1048576000, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 256000, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1048576000, + "byteOffset": 0 + } + ], + "md5sum": "c5d3083a8d2422daf2610c41497cec40" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 131072000, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 256000, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 131072000, + "byteOffset": 0 + } + ], + "md5sum": "7803fac45026b4eb384f417c0280667d" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.0.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "0afc7229eae1c639faf96b6260671d94" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1b91984460baf05b58779a4c13305791" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.0.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f2c07997dfce37433288314e92a3f67e" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "3c1478590723af580bea955d3f87caa1" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.0.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.0.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "42c89d53adbb12e7cae97c2ca6351a86" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.0.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "bfd2e487577efae3ee789fe63f196604" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "53f803d643cf981f6c351b99c2f05701" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 25182208, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25165824 + } + ], + "md5sum": "fed82e0fa7c3b451ac98c6fd77a50bcc" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.1.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "e4901c356dd921daaaaabeb4e93ed045" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.1.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "8ba676e3cdbdc35fb3458a22934f2b54" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.1.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "5bbd566f342f53fd8d8dc1f8c73c630f" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e5ee649a9f770cfa219cf6feadb25d1d" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.1.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "079dd6ebb390f9d465f2223f6fe1d6da" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "adb32162fa406916fb0c014a6221067d" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.1.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.1.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "03a2807d916a555288256c9abe0cac88" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.2.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "afe5bc10f587902b1c0ceaf606101bb3" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.2.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "944f559b66186092f678817827f2e2f0" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.2.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "84f09462e4dc4f6900d6b2a500544196" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c76fcc04383e93295c80717faffb6050" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.2.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c1e7030e13b7630f71838a60849b7b95" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.3.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "7b1950ca371f6ad968f75f410a8d9e1d" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 22020096, + "records": [ + { + "name": "model.layers.2.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.2.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + } + ], + "md5sum": "f9a63d3eef7c3c737abdbd0f76db0219" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.3.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "686d8883378b018a30e369c985db3335" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "90633cf233a2913b73fcbe1e30c7e457" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.3.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f2e9330bd5bb74b6ccb03170ccc241f1" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.3.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.3.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "725cbe3e3ffdbdcaaf19ab5fa56731d7" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "3da1933d4a1e62263e44f96c04cfb3d2" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.10.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "edf897db0117039e83845b1c45698c64" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.10.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "4194510b9f1ce6b5089bec74593fb195" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.3.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.10.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16793600 + } + ], + "md5sum": "f48d4e86bddc15bb0e9a3b2b3a4591bc" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "0a269c9285d58e94a92c01de8a0a7f4c" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.11.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "38d90096f46c2d30cb78ea7ba371a91b" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 25182208, + "records": [ + { + "name": "model.layers.10.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12582912 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12599296 + } + ], + "md5sum": "75db9789bf33dd881bc650534ae6e901" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.11.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "59947d599054123161fd0ea1ebbe4801" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "3406c5420dc22c98b96516fbbf92d0b0" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.11.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ca886e8e77d7b3e0da0818c48c83ab83" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.11.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.11.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "0c4bc3848e8a9967d79def11eb09efd2" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "b668d5aac90dcef2dc5a7a41e241ea6a" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.12.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "1f3d89755746afdccb5154f349b8ba1c" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.12.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "44cdcb58cdf5bcbbbc51a39362e9ce75" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.11.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.12.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16793600 + } + ], + "md5sum": "da697ad66fefd5df7f471044783f7c46" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "fd7c16477b79550e26b4cec4ce235d5c" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.12.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c9d30538fb9ec34f56774cf9adeeaf3d" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.13.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "f169df3a7bb7bb647c2d325d94f4607c" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 22020096, + "records": [ + { + "name": "model.layers.12.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.12.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + } + ], + "md5sum": "80e9f45401330eeb99ce84726a4d8498" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d689223b8f75218b32b9b7f9a8969c1c" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.13.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "037cbced0d23236d0d9ec3bf674e76cd" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d6098063522b220cfd18c6b1d12535ac" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.10.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f406b7ebc6f7695e02c373f3a68af4b7" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "917e4c38575ec3db8da3e0c357d897c6" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 31473664, + "records": [ + { + "name": "model.layers.13.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.13.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 22020096 + }, + { + "name": "model.layers.10.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 27262976 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31457280 + } + ], + "md5sum": "91f74fb6625af2bff9e50c2897e7d625" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.7.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "ba69d653615b49c77dfd3cfeee076db9" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.7.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "ba8533f1fca7c25dfef335fd69d475e2" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.7.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "9da80bb55a6a4cbc8e1df3b54ce6f7f5" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "3b2c120b449054347cac15895aa84f29" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.7.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "405f3edc7a45d9c744862da373043043" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "015e81dda9a55129afc029751083c070" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.7.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.7.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "9a534adb4949e7a2c050ee0d856b1c8f" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.8.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "d51576deff9cf5bf75287e149bfb58b6" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.8.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "2d6ed7e5889220dde7b91c404c2d81cd" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.8.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "2ed4c1b2b1a441971b058cd92f1e9268" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5ad96899a5ba1307226ed6b142d1b950" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.8.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1ffa378d0d4fbf4a5008c8ea0b6cfb8b" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "abe9dae34a4e82ca780e99d3caa4dca9" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.8.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.8.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "18f917be7d3f8de0d35abeaf86dffa4d" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.9.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "548dad444ee926b5fc0136e18fdd0a7e" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.9.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "24e98f9c20bdcc642d89c7bbbfb03b3d" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.9.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "652b846ec021a280de26e927073de0fd" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "f749f74fedf9a0f67bad4ae8ba29c7d5" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.9.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c8ec70a873be313309ac711a95563115" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "68281413defca344d3cf843f513edafb" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.9.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.9.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "0ad094bea81b706b64c3be254291f8f2" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.13.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "c7a1dd448ed473d7b99969ea577b2924" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "8d3d7f403e4c860f9ed4880653581669" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 25182208, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.13.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25165824 + } + ], + "md5sum": "fa43d51bffbea4113a199e44b2a459c9" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.14.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "f08490dfe9dc90d32d434416b536ccd6" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.14.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "81cb7466454d52fcf006af172f19f450" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.14.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "76da0419d600b090617b43b7a2e3dbac" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "94a248d8a4f6ef8f84ccc450847924c7" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.14.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ff0db7ff6165542413f02e4cd2c1985f" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "c93767584728faabfff9ecb2b58b9a0e" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.14.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.14.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "478bb4e7a1bf868a5885152a04369330" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.15.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "65c906cc2701e6f2d2a84304ce773744" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.15.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "6ec4687ee858e51f77d1c4fe4f204473" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.15.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "e3dab2848244f765e36d9196a78ebd94" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0ec87181e257c60eb1a2ebbb7021308e" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.15.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "19fb8028f448d429be7606a231d850d1" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.16.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "7f5444a1116a8c987a889d09883dba66" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 22020096, + "records": [ + { + "name": "model.layers.15.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.15.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + } + ], + "md5sum": "11fcdec78b92b76958e71655980c98fd" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.16.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "1cbffa7320e0a769fae1e4dbb33e6400" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1127a41b2436a11b54e120422130069a" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.16.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2742c6ae91c91130bcaf0111960058a1" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.16.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.16.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "4c78f8190bdc62f552d8984ce90fb903" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "fb46ae4159883080a34d6b441f33f917" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "aae771fb01ecd01f5d37d1d159aff989" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.17.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "7869cd97245e9cb5bfb7fedeb1ca0243" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.16.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 16793600 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16809984 + } + ], + "md5sum": "2c00ec279c700fd6f51b0c021ce59726" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.17.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "1c5ef2f9c2743f442b28cb838bf86cff" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "37cab0c86b9a9c9eb516befab94b5ec3" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.17.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "15dea361ba7c95cc842a6c6022b9f33e" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.17.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.17.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "2e0a031c58b69af93f8270c8567d6417" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "83e7e3facf1dbf309df1fe3d5b087470" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.18.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "3b07297464f268dd52ed12231d2eedbd" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.18.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "00a10d74afcd1e3f2b2429c4be0cc573" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.17.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.18.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16793600 + } + ], + "md5sum": "6631e2352efc1e043f0eef1193dbf91a" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "993ad5d624ba876219cf66cd2bd83387" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.18.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3450f3cb9a3b3838b4c8ec5c711469e3" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "4dc67f53973ed09eb2376f511cbf311c" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.18.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.18.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "2996772cb075a3dbcc7b20ef79fc8fc7" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.19.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "dd9f5c700653da2587cd2deaa1965e82" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.19.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "14642b02b288186c66d6bfaa739ac2c3" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.19.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "2fb93bda10a9399a95115b98aad0cf1c" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "367be01a41c50f2d3b7a1509d905e2cf" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.19.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b772e6bf541aeb748e3945239bc92a14" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "be01e96c3a6e1e377d1f6874684f7ea6" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.19.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.19.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "495bdf1bf40d8b14b36266169b2d2a48" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.20.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "655cb4f25810c8f90181f5c7bce02208" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.20.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "d2206c47cdfa657d10794b69df10b9c5" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.20.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "4ae5027e39bb6bd3846daaad68045f86" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4cdfed76ef491702013ab7648330cdaa" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.20.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a0f6359cdc39d60a6aedb4a49b3c79fe" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "11a3b97435d1c5d7800e68393ef52121" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.20.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.20.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "17257d7b5af3db95e963f687b4a5c6da" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.21.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "7671014de5b454551a343f85f0109ac3" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.21.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "b5a86d1864e732f004a34d80051ba768" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.21.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "2d7a1c28dab3b70b797674da26155aa4" + }, + { + "dataPath": "params_shard_128.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "90766be437f1368f8b276f52495dd0f1" + }, + { + "dataPath": "params_shard_129.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.21.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "199c94fd208aa04aaa9068a1029abbb7" + }, + { + "dataPath": "params_shard_130.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "f2aca788f52705fd85967475c2d21577" + }, + { + "dataPath": "params_shard_131.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.21.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.21.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "13030cefb4e3438db73dfe950be2c1e3" + }, + { + "dataPath": "params_shard_132.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.22.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "ed664daea3633ef3e9308c18be257cbf" + }, + { + "dataPath": "params_shard_133.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.22.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "80478eb1621720dbc7c2fbe1ba4cfda1" + }, + { + "dataPath": "params_shard_134.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.22.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "407fa906d3d59ad97e67be1d1214d47d" + }, + { + "dataPath": "params_shard_135.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "57d43cc6b138c2a87ffcb5c5d63c2fde" + }, + { + "dataPath": "params_shard_136.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.22.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2efbdf41a1b27b74298ea63bb4de78bc" + }, + { + "dataPath": "params_shard_137.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9ff16b92fcc55496bb68a685aacf06d6" + }, + { + "dataPath": "params_shard_138.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.23.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "081ed74f16224b00a516969822bd3333" + }, + { + "dataPath": "params_shard_139.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "e4fddb5dfdf50023bca7e1c5a83cd3a9" + }, + { + "dataPath": "params_shard_140.bin", + "format": "raw-shard", + "nbytes": 31473664, + "records": [ + { + "name": "model.layers.22.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.22.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 22020096 + }, + { + "name": "model.layers.23.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 27262976 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31457280 + } + ], + "md5sum": "253614d5205de802a378c2b94bb42c57" + }, + { + "dataPath": "params_shard_141.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.23.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "bb867b647c2776c7d4c41af83e46d532" + }, + { + "dataPath": "params_shard_142.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.23.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "8cbb37a698fab5227021e126696c3170" + }, + { + "dataPath": "params_shard_143.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.23.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "0bc0a49c78d18553f5564de70f9e7bf9" + }, + { + "dataPath": "params_shard_144.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "27e76439a97e8818e4c65f94ae5e3f39" + }, + { + "dataPath": "params_shard_145.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.24.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "3df912b130150912f7bfb04e9581fd5d" + }, + { + "dataPath": "params_shard_146.bin", + "format": "raw-shard", + "nbytes": 25182208, + "records": [ + { + "name": "model.layers.23.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12582912 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12599296 + } + ], + "md5sum": "d50f7eed9eeb03756832db326d0ea418" + }, + { + "dataPath": "params_shard_147.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.24.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "febebbeed03e4ee55b884547f182dab1" + }, + { + "dataPath": "params_shard_148.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4aea462cc5cc9d6752889cf51a54f5a3" + }, + { + "dataPath": "params_shard_149.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.24.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "8363cbc4da7eb114810f018fa61cefd4" + }, + { + "dataPath": "params_shard_150.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.24.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.24.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "604b3b48077ea664ca891f25a8772a1c" + }, + { + "dataPath": "params_shard_151.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "54adc99b63645320eca047a0d53002fc" + }, + { + "dataPath": "params_shard_152.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.25.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "ca67b637983f73b6340a12a6ccb3b45c" + }, + { + "dataPath": "params_shard_153.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.25.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "883be0d729fc369e3f8c07f52b15cf4c" + }, + { + "dataPath": "params_shard_154.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.24.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.25.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16793600 + } + ], + "md5sum": "e6f5701d0e23e244c65a4ad8a1c2abc7" + }, + { + "dataPath": "params_shard_155.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "78cd3b237390de448a7d9517eb18ca04" + }, + { + "dataPath": "params_shard_156.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.25.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1b277acdc6d03d212bb3525db57ec101" + }, + { + "dataPath": "params_shard_157.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.26.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "a98938f7e5b46f699da8a8232241bcfd" + }, + { + "dataPath": "params_shard_158.bin", + "format": "raw-shard", + "nbytes": 22020096, + "records": [ + { + "name": "model.layers.25.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.25.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + } + ], + "md5sum": "2739734e3cd89b2ef79360e9651837f2" + }, + { + "dataPath": "params_shard_159.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7d9c021ea3e9e5fb13ee034ffc116943" + }, + { + "dataPath": "params_shard_160.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.26.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1372ec4418bdc3e96b8feff440f66c56" + }, + { + "dataPath": "params_shard_161.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "2796a759be023fca18c4e49b2a3b4ba0" + }, + { + "dataPath": "params_shard_162.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.26.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.26.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "3e6218b6c95f476ec4cbc8d7eb030104" + }, + { + "dataPath": "params_shard_163.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.26.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "95fd8aef850cdba19793ff8ff433781e" + }, + { + "dataPath": "params_shard_164.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "012c331c996b173e946f0bb5ea397ae2" + }, + { + "dataPath": "params_shard_165.bin", + "format": "raw-shard", + "nbytes": 25182208, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.26.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25165824 + } + ], + "md5sum": "b3885da6335e2090600faef6f7216c64" + }, + { + "dataPath": "params_shard_166.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.27.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "efc4cd6c926916d01d90697347734b2d" + }, + { + "dataPath": "params_shard_167.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.27.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "d21b913c175a28da5b67c9725ef16a6f" + }, + { + "dataPath": "params_shard_168.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.27.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "920158616356d9fb750713ed0e8ca0e4" + }, + { + "dataPath": "params_shard_169.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9ca35b4e3a676c595945f6b7e9fc4810" + }, + { + "dataPath": "params_shard_170.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.27.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "adbee9e546334ff25f1cc376fce2d95a" + }, + { + "dataPath": "params_shard_171.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "9ebedb7dd3e1c6b6a81ef5a52bfbe2c2" + }, + { + "dataPath": "params_shard_172.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.27.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.27.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "af12949f9a754ddcfd9c2fbd0cbae023" + }, + { + "dataPath": "params_shard_173.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.28.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "71f3fff4cd5d55f0139c37032e9a7bb4" + }, + { + "dataPath": "params_shard_174.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.28.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "0ee5c5d9d64f80751367c7cd40d0f69d" + }, + { + "dataPath": "params_shard_175.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.28.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "6376598b3f7d25978390e336d9e2da7d" + }, + { + "dataPath": "params_shard_176.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b3f54f027d412bc0082868438cd57ed3" + }, + { + "dataPath": "params_shard_177.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.28.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5411a9d9bcccd8ec61298a9e1a3a4946" + }, + { + "dataPath": "params_shard_178.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.29.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "5877862e949bc1e260c9aa932b1ca47d" + }, + { + "dataPath": "params_shard_179.bin", + "format": "raw-shard", + "nbytes": 22020096, + "records": [ + { + "name": "model.layers.28.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.28.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + } + ], + "md5sum": "18e9b23348e69f1052442ad57f165a4d" + }, + { + "dataPath": "params_shard_180.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.29.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "36ceee473da91077bdd4c9ae0c6b3e8e" + }, + { + "dataPath": "params_shard_181.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8fd0c54270c792fe5560bf3f7efc0198" + }, + { + "dataPath": "params_shard_182.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.29.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b70c33126a3af7c7b972fff3254b8d3f" + }, + { + "dataPath": "params_shard_183.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.29.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.29.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "bea5b7a41b57226ba5b8590aec474e3b" + }, + { + "dataPath": "params_shard_184.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "4c0dd84b7531b769a9e7d0f27229a694" + }, + { + "dataPath": "params_shard_185.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "fe31a3ff8ec2470c39e56611731d37d6" + }, + { + "dataPath": "params_shard_186.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.30.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "de1e1ac0224210e08d27d9ebea80c9b2" + }, + { + "dataPath": "params_shard_187.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.29.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 16793600 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16809984 + } + ], + "md5sum": "d92fa4ed737b5fbb947da65531cb6e0b" + }, + { + "dataPath": "params_shard_188.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.30.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "b3e074b27aeb78002c61f652ccfd0b3c" + }, + { + "dataPath": "params_shard_189.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7d17c52fb692339750b24b76d2a8ba95" + }, + { + "dataPath": "params_shard_190.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.30.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "91cdf175a3941e4a5eb4394c04d35cd4" + }, + { + "dataPath": "params_shard_191.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.30.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.30.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "cd65c9ec052b2318fea7736e1567f013" + }, + { + "dataPath": "params_shard_192.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "8948ede8e2d3b135c7e03356a4029c3e" + }, + { + "dataPath": "params_shard_193.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.31.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "75cf21a649b1e5d5f09c2e828d2bb019" + }, + { + "dataPath": "params_shard_194.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.31.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "23a53fb92652425f539b2ab7ff532bc2" + }, + { + "dataPath": "params_shard_195.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.30.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.31.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16793600 + } + ], + "md5sum": "4c26d7045b8339b0519930cdb0bbffd6" + }, + { + "dataPath": "params_shard_196.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "09c04e2ee2608e8e7563dc653f8c9085" + }, + { + "dataPath": "params_shard_197.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.31.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5178d2eb7e8d28c95f4ac30e1538fbee" + }, + { + "dataPath": "params_shard_198.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "78e488566db95738296574ddd47e58d5" + }, + { + "dataPath": "params_shard_199.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.31.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.31.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "78e1e1e5974a206e5c66b94b01998cd6" + }, + { + "dataPath": "params_shard_200.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.32.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "911e19d18e62f55a6377d85cdf79ef90" + }, + { + "dataPath": "params_shard_201.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.32.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "5175e14d1babdb641505d3d225213028" + }, + { + "dataPath": "params_shard_202.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.32.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "9ba4a16ff6ddf0ac05b5ac84a46e72a8" + }, + { + "dataPath": "params_shard_203.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e261f0f837929c1353eea9bb62dca829" + }, + { + "dataPath": "params_shard_204.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.32.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0a6690417d9c40185d4aa3a6079e0acb" + }, + { + "dataPath": "params_shard_205.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "0eb24a0d0f54ba6c56319a9ca758406e" + }, + { + "dataPath": "params_shard_206.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.32.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.32.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "1e070d79aae81a1fee5471080d03706b" + }, + { + "dataPath": "params_shard_207.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "3be032f6fde4b0e2c9f06a00a61d9752" + }, + { + "dataPath": "params_shard_208.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.4.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "fc6241a3cb59754735cc2d80b492934d" + }, + { + "dataPath": "params_shard_209.bin", + "format": "raw-shard", + "nbytes": 25182208, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12582912 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12599296 + } + ], + "md5sum": "cf8167ca3822a2425c8465945af0124f" + }, + { + "dataPath": "params_shard_210.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.4.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "79cd624f93cd67ee7dbe9c81a86f4ee0" + }, + { + "dataPath": "params_shard_211.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "01d03f90201c018cb9c7684240e0ab3b" + }, + { + "dataPath": "params_shard_212.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.4.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "42a88c5e991f56bce906684ec52b8ad0" + }, + { + "dataPath": "params_shard_213.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.4.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.4.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "ce528af5c7a5b5b5d69907e120110876" + }, + { + "dataPath": "params_shard_214.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "f1d4a53f2a843cef2f0e7e02b2d242e2" + }, + { + "dataPath": "params_shard_215.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.5.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "0991b1a4a33776ee2502664f69834c38" + }, + { + "dataPath": "params_shard_216.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.5.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "e2d67bbebf8a4c55139918775c7513ec" + }, + { + "dataPath": "params_shard_217.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.4.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.5.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16793600 + } + ], + "md5sum": "714f0f1950bcc69858b4907c83826396" + }, + { + "dataPath": "params_shard_218.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e7b47ab702cf311fd65950e0b6e68e4d" + }, + { + "dataPath": "params_shard_219.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.5.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5170efffb9e4c7d0a8d75395894132d3" + }, + { + "dataPath": "params_shard_220.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "06483c2b255842e78204368a479eccb1" + }, + { + "dataPath": "params_shard_221.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.5.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.5.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "6ef7f176a06e94352ed0baf0bff1984e" + }, + { + "dataPath": "params_shard_222.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.6.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "aa8a768fc3d7c7c1b692d813bb394193" + }, + { + "dataPath": "params_shard_223.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.6.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "e68a6b600dd18121bc0e0446fd48badc" + }, + { + "dataPath": "params_shard_224.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.6.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "648c4b4062a80a75cf6408023b6e8901" + }, + { + "dataPath": "params_shard_225.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4eeab07ac289ae1220341569749ba8bb" + }, + { + "dataPath": "params_shard_226.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.6.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "43cd0011a165b7f4fbb269b919934c27" + }, + { + "dataPath": "params_shard_227.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "fe79c2bf46b6bfe9f0c15d428645beed" + }, + { + "dataPath": "params_shard_228.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.6.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.6.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "44fc71eda2ae0a0e3c7445d8f903b21b" + }, + { + "dataPath": "params_shard_229.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.33.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "5d6d8433304184cc5d97fdb2bffc6782" + }, + { + "dataPath": "params_shard_230.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.33.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "49e67bad8e07a96d58c588321eac19de" + }, + { + "dataPath": "params_shard_231.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.33.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "a2405a01971b42ad2e2908e6d316c6e3" + }, + { + "dataPath": "params_shard_232.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "78effae2f932c438d62ad2c573a34578" + }, + { + "dataPath": "params_shard_233.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.33.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e77e05ff758051bbce50fce302e71cd5" + }, + { + "dataPath": "params_shard_234.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "36a79fd9dac2c22e97eeea2ab5813994" + }, + { + "dataPath": "params_shard_235.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.33.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.33.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "2d801bcab451a0742c7b6f9bf65e9673" + }, + { + "dataPath": "params_shard_236.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.34.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "d479c98ba0ed88bb8f8bfbcd9282b6bc" + }, + { + "dataPath": "params_shard_237.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.34.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "777c53d37f58448e61ee7dfd2ca8124b" + }, + { + "dataPath": "params_shard_238.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.34.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "4e4d4f4c232e4445bc9f89d7bc95012b" + }, + { + "dataPath": "params_shard_239.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "deca0639b0ccef6bb27fc0e512489b9e" + }, + { + "dataPath": "params_shard_240.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.34.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ee44f2c06fdcf9e12cb4e5370c0c788b" + }, + { + "dataPath": "params_shard_241.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "2a35d2d0db32d2e8afe6bb1305440f51" + }, + { + "dataPath": "params_shard_242.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.34.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.34.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "1380ba41e27b95e4e1412704e004c6df" + }, + { + "dataPath": "params_shard_243.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.35.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "5c416e5c89ec8817abd2ab846720d9c0" + }, + { + "dataPath": "params_shard_244.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.35.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "f88c1a5a019f1666b8ce54f05d0a1f2d" + }, + { + "dataPath": "params_shard_245.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.35.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "62591bfb3a04cad63af54edab2567674" + }, + { + "dataPath": "params_shard_246.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "76c78b06f7c8b9cd6ddbef59abbe6b6d" + }, + { + "dataPath": "params_shard_247.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.35.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c198d239a04aebb43686abca3d18f85b" + }, + { + "dataPath": "params_shard_248.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a569ea42fab92c3da4b1d6856293ac24" + }, + { + "dataPath": "params_shard_249.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.36.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "64d3e0da35a237dd06d1ab7923a5e30a" + }, + { + "dataPath": "params_shard_250.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "0ed7118aaaa0aa982ac26216ec129108" + }, + { + "dataPath": "params_shard_251.bin", + "format": "raw-shard", + "nbytes": 31473664, + "records": [ + { + "name": "model.layers.35.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.35.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 22020096 + }, + { + "name": "model.layers.36.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 27262976 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31457280 + } + ], + "md5sum": "1ec2260ca83366c0d82b205ddb074816" + }, + { + "dataPath": "params_shard_252.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.36.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "fdad05fa73c5aa520564b4d1ff014020" + }, + { + "dataPath": "params_shard_253.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.36.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "0af6a81bd74a8640fca3d877b41fb836" + }, + { + "dataPath": "params_shard_254.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.36.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + } + ], + "md5sum": "c59a0f911667811a32eb8f79eb2edf18" + }, + { + "dataPath": "params_shard_255.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "987c2303266ef4bf72bce6e6fddb686d" + }, + { + "dataPath": "params_shard_256.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.37.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "d361fa9fd4f1d532cb97fbb05dcdaf41" + }, + { + "dataPath": "params_shard_257.bin", + "format": "raw-shard", + "nbytes": 25182208, + "records": [ + { + "name": "model.layers.36.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12582912 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12599296 + } + ], + "md5sum": "340e73f5b4c4942fe2539a9fc79f59b1" + }, + { + "dataPath": "params_shard_258.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.37.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "def9e645888cdf9276216a82e15786ef" + }, + { + "dataPath": "params_shard_259.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "26c03b8779ac0c2c83f163dea7662270" + }, + { + "dataPath": "params_shard_260.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.37.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3a53777ec83764d049d500d065dfcb0f" + }, + { + "dataPath": "params_shard_261.bin", + "format": "raw-shard", + "nbytes": 30408704, + "records": [ + { + "name": "model.layers.37.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.37.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 25165824 + } + ], + "md5sum": "a9525c5314c0cc813a1a56ffe761cba7" + }, + { + "dataPath": "params_shard_262.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "fadcb5d67060b71bb3e4205a0fcbdbef" + }, + { + "dataPath": "params_shard_263.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.38.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "a72a090402be0649130c7a217297da02" + }, + { + "dataPath": "params_shard_264.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.38.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "3ddbfdf5ddc4fc19c283bc1c9bb7efe3" + }, + { + "dataPath": "params_shard_265.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.37.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 4210688 + }, + { + "name": "model.layers.38.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 16793600 + } + ], + "md5sum": "f44f4b29331fe6735429ef373f4ad943" + }, + { + "dataPath": "params_shard_266.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "303b5db25f694fa910bc3c8509f6f515" + }, + { + "dataPath": "params_shard_267.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.38.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c4e795e1e0ee7fa92192db669292920e" + }, + { + "dataPath": "params_shard_268.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.39.mlp.gate_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "5ce24bc64a32d89be5a66db99299d1ca" + }, + { + "dataPath": "params_shard_269.bin", + "format": "raw-shard", + "nbytes": 22020096, + "records": [ + { + "name": "model.layers.38.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.38.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + } + ], + "md5sum": "7ccebedeebcbc25f099478a886939fc5" + }, + { + "dataPath": "params_shard_270.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9bfec26212f6153695a7bf94b7ed8901" + }, + { + "dataPath": "params_shard_271.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.39.self_attn.out_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "43c4a501ae5c0677f3777f18969abf1d" + }, + { + "dataPath": "params_shard_272.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3072 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "368521515108205d26c5353b9cfd6b5b" + }, + { + "dataPath": "params_shard_273.bin", + "format": "raw-shard", + "nbytes": 22036480, + "records": [ + { + "name": "model.layers.39.mlp.gate_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 12582912 + }, + { + "name": "model.layers.39.self_attn.out_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 17825792 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22020096 + } + ], + "md5sum": "472cefa815c9075f98e8eddcbbaef27d" + }, + { + "dataPath": "params_shard_274.bin", + "format": "raw-shard", + "nbytes": 100663296, + "records": [ + { + "name": "model.layers.39.mlp.up_proj.q_weight", + "shape": [ + 24576, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 100663296, + "byteOffset": 0 + } + ], + "md5sum": "e09c7ddf26c54324ae72d9484eb8b736" + }, + { + "dataPath": "params_shard_275.bin", + "format": "raw-shard", + "nbytes": 25182208, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 8192, + 768 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.39.mlp.up_proj.q_scale", + "shape": [ + 24576, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12582912 + }, + { + "name": "model.norm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25165824 + } + ], + "md5sum": "5f0b7ad0570878b150bf0d46ac6a1a03" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..f3f618cf9b450ca027a655f311e784fba7a04db2 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9af90520f4a5b06e967ffd246f0c224a9cac05746703c1ee1def76bee2b498d +size 1048576000 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..c39d1c65a50cc4ecde0e057769616c7a8dd7e49e --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f072fe96910774a3cb719c286b428d59424b6262501207eea30cba66e7d3060b +size 131072000 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f4b50457e558ca901ff5e97d5a41cd8a2a4df6e --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cc8575fb6fe6529f3481424ea8c669e61bf4ccc02181e08e8d861344c8f5be5 +size 100663296 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c64bd9700af55fe4564906e75a36e46480d2493 --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f301d534331def8994c8beb9aab4233433fb4aec4791763d5ae1f823bbae774 +size 41943040 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..c6fa2aced9d8f950ad9829a9ad21d834fb7615f7 --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d1639f118a938f071c2df18363f5b478f70a87953c429cb0bdb28946cba855 +size 33554432 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..9cf717a7c785aa626063d7ad11667bc9675516e6 --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d86c25de2091a82b7a116aae8d879ae40b4c6f15f630d98d36a67918acc581 +size 30408704 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..c939748e479e272248c5f4343a8eb2d40f270b46 --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562d79aaf64398d855a62723b34f825346945e795bdb4270cdfde498ecbc161f +size 100663296 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ef901e20d95a9e28151e96f80b9b587770f10fd --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776febf12ae1adfe3492e1bce1f59c6c52eb8d3bb0c17d55fd5c711fd102aa69 +size 100663296 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..2064d8a1a2954764e07c09a43dba6c115238cae6 --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773a28a75d74cf27ff5413cbe13c1b5f347a0090adab459ef273557a44a81e57 +size 100663296 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..11e896b7615e77616bcc533b85d38e3c5096b1b4 --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ead38fb3b900349e8df9d15201375fa6449dc7eb069e5787b8bba7481623b97e +size 29376512 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..b93fbb784f73fb2df843544ff30fa3fbad647308 --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68390637ae684bd3614fd79aa30c66cb852406d8bd39cae77bf7f7172b02f04c +size 41943040 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..a53074c1954a33d3ebf8cafb6ee56da296285e80 --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32738a4ed866836d76f80d23216cbcdb3c169a951ba80a7396f42a333f61bc0c +size 33554432 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..d484cc1842417b62b4ef94ff531973d543d3b59d --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f67f1430beb805deca44a5b2f580ad1b899cdd55005c66345008b1449fa1d807 +size 100663296 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b60b689a1372d4f15f339ce740809dc5b22bceb --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:024bad1bc25440d0902f51af2aa530c0a51e798c3d778b68cd38ce1a62787276 +size 100663296 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..0136ac9fe8c636fd6d0e8dd064174177439a415b --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e095cad69728bd0c5db2777283fad0e40c58d4ad1b20e1af360d1296d760fc +size 22036480 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..f01155b733e82ac76e45f67fb911770be217cae0 --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:724845c80938f509d88ceb114108dc936a397a038dff8bcf85fb1447aa036d29 +size 100663296 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..2194a01c2f5a05d6e3ca52d956260748b21b4180 --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b59ecbadeff1b53f42859950db53c6f4578d3ff47e75d217ca5c95d03aa2e1 +size 100663296 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea8537c7549d3cb72b84e6c481ec5ea81a196960 --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1731654893ef95e782bfd10cdaf34b5b035ab820516b52fa3239a781202ca867 +size 25165824 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..c11fbeeba5ff6a7c4e8484557505ec4e394a7808 --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc35ffa5657bbfc1b173983ec66025487c4bb03f6f536034987322cb12294eb1 +size 41943040 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..ff7db56a78b4278eb1fedbc4d8f094757b37a9e7 --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdc4103fd287062df029109d54ef7a40c50fbbe667cdf9c99dbba49b9af5eec5 +size 33554432 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..81c966cb95b28a2b2b7910b945e9151e329fb5fe --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3edc3e26144230785cfb794a4dc389761c4e275122b0c7a37a7fd091f6c8337 +size 100663296 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..7960cf458fbfdfd4fa42fc8368f266590422e117 --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aabe22f54942d1c805535559d6e7ba3b8a2095d0704d16f189a65a38c953381 +size 22036480 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..80ec140803b07974027c4fd2f57a62546dbc6d74 --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10937549c4f7bbc5443860ac14ac4b4c4f96f7bbe7b783c3991a16e8bf062721 +size 100663296 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..0a3d8dd2ef0df12cc36c473a068b4ce507a0193a --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2773b9e86e9643eceddf148e0e9ceb190bad80534b390ecd5afa102a4ef730a2 +size 100663296 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..38073506aac9ead3cae02c8d794b605e94bea2bb --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c8f09d02c02575acaebb1c6df379dca05261040d46fedbf21d79374ee4dce6 +size 25165824 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..59bc05d38e11cc43e7940071213327817c2e4329 --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6d5bfc6835a2811769b15058a6beda4077c9b1232228109ae281c717ebe870e +size 25165824 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..fcc3b94c53d6dbfed57d43fed42aa9ea56569875 --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81f081e8c692c2f636df07be41355a5cf9aaa919472872bb741f0871125aa8f +size 41943040 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f8606803b31f795987834e80158f21ba9c5d54c --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4b8605ee2f5db8ab85ec244c0000df838fbc8a080b66da3f146af2fdc1c72d +size 33554432 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..1823888295255e603691f09c2dfa538ca52ce07a --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38e723cf3eeb9d236f587171f7cee67a2f9fd8f6fdef151173a698b313cfe1e7 +size 100663296 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa568dc80f2f450d7edb179d315f5a83e2d8a689 --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856f32627e54eadc64a7fcd2bf4eb7687abee7fa61cb2791fe9999ccfa1c10af +size 22036480 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..af57bba20fccadea477da5ea066b6c97b2bdce44 --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939fbfdebdc27338d9d2cfa941943c1584f1733a8f40c2d1450547b0de47cb88 +size 100663296 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..aedacdd3debaa93bc992714c7a0a2da682ba4f99 --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a8fc326f48b8ee77f16434e0071db55e7ff515cee58b02213eee4fb9eafe5e4 +size 100663296 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..3fcce77f2afc53dbb4c5e1fd207661b5b4ea16d6 --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98908b2dcfe2713b7e15043c3da8ab8e7510782c7b99c994f0bc5dca68d039fe +size 25165824 diff --git a/params_shard_128.bin b/params_shard_128.bin new file mode 100644 index 0000000000000000000000000000000000000000..dcbc0ca2a213240315b2e05814f8c8ef1f62ede8 --- /dev/null +++ b/params_shard_128.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ccc490e03a8b677145425f88f5616c534890ad3f481169910d7b0a0b4a6504 +size 41943040 diff --git a/params_shard_129.bin b/params_shard_129.bin new file mode 100644 index 0000000000000000000000000000000000000000..171ab513931daa74c5643c0d11125b20e5745b3a --- /dev/null +++ b/params_shard_129.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9445c63fb0a4cdfad9ad47014cf3fbd711a68bc8f333734e3a2a10437f889d38 +size 33554432 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..6868e078cfb9908d25636a2ecb14f1bb37d4e8ae --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e676226c16f4373a4c1b5a85f3687834401fb60f3c6a3ee6a75e35ebf7740ea +size 41943040 diff --git a/params_shard_130.bin b/params_shard_130.bin new file mode 100644 index 0000000000000000000000000000000000000000..d64f7dda7a13f222935208b2eda0ae49362b6c1a --- /dev/null +++ b/params_shard_130.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5501d3a7511e92b7acb5d6007193ffc3975e3d7d44c1c4e60295c6be107a698a +size 100663296 diff --git a/params_shard_131.bin b/params_shard_131.bin new file mode 100644 index 0000000000000000000000000000000000000000..f80af7c40271cf1d680a3cf92ef0b7261d26c8a1 --- /dev/null +++ b/params_shard_131.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c4a608d643e4b4091f4bf972ebce8e5d2338eb22a7b0072d17433e20ef4750 +size 22036480 diff --git a/params_shard_132.bin b/params_shard_132.bin new file mode 100644 index 0000000000000000000000000000000000000000..91a91d598e12cfbcde536f9c6fa4fc3fadfc8e6d --- /dev/null +++ b/params_shard_132.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112dd3d1f55ee04340e09080464fecd9e32678bd5b6d800e48ece8321fccf832 +size 100663296 diff --git a/params_shard_133.bin b/params_shard_133.bin new file mode 100644 index 0000000000000000000000000000000000000000..848b0ede51008156a2eedd4251e7b032d296027e --- /dev/null +++ b/params_shard_133.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0bcb210826282c0f7fa72935cdee346ce1c841ee1ad1b3e1c25bc3526f1251 +size 100663296 diff --git a/params_shard_134.bin b/params_shard_134.bin new file mode 100644 index 0000000000000000000000000000000000000000..9f0b06e3dde77b79b1f51f15f95e14f16d4bca82 --- /dev/null +++ b/params_shard_134.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a4e51d4c2889294dd8f3c6e87683778839d3dcb3704f881f5adc001fd879e29 +size 25165824 diff --git a/params_shard_135.bin b/params_shard_135.bin new file mode 100644 index 0000000000000000000000000000000000000000..2114775f4b34f7779043f3e6a9c6aba39b670014 --- /dev/null +++ b/params_shard_135.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8cbf712f70018c13788c20f940687d5012d800dc5940c27884ab9a2256ee99 +size 41943040 diff --git a/params_shard_136.bin b/params_shard_136.bin new file mode 100644 index 0000000000000000000000000000000000000000..c341202ca211f77a1298d6495758ec1f4d577b6e --- /dev/null +++ b/params_shard_136.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e48b84ddfa54850e68cbfc5d4e3483e802d49bba207cc86b4ee8e215c30c6f8a +size 33554432 diff --git a/params_shard_137.bin b/params_shard_137.bin new file mode 100644 index 0000000000000000000000000000000000000000..70c65c0765ea70f22b76a5cac3e34f35b41881e1 --- /dev/null +++ b/params_shard_137.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49227e7dd8058b9104ad4324a51d6b929531c9e09bf866492a67e2b3ed028bf8 +size 41943040 diff --git a/params_shard_138.bin b/params_shard_138.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a1f0473684ad8cdc0d19fbd86395a91a0250676 --- /dev/null +++ b/params_shard_138.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37200147e3e3ba20999807428ab2b1c8ad5531e1721846b46b7732e2f78b97bf +size 33554432 diff --git a/params_shard_139.bin b/params_shard_139.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b2e1c7817d5cc63bcd6a0d5042e8d8afcc996ed --- /dev/null +++ b/params_shard_139.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b020cb7d79382ac701e03f0af3d654f5666e05f2011c3170269842d4385a0dde +size 100663296 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..226523d61e55e44990aebea1567deea184f49b11 --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e2df686859515b5df672ea1e0142236978aed8720bcb865683fb5c112f54db8 +size 33554432 diff --git a/params_shard_140.bin b/params_shard_140.bin new file mode 100644 index 0000000000000000000000000000000000000000..8fff6eb8651547375caf2a390945423830a21867 --- /dev/null +++ b/params_shard_140.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:621c02ef003356017a1f784cf0a8e190855dc05fc208c7c7974e99634610fd43 +size 31473664 diff --git a/params_shard_141.bin b/params_shard_141.bin new file mode 100644 index 0000000000000000000000000000000000000000..091b067e016f588d08af1d789b9c531932dc9c98 --- /dev/null +++ b/params_shard_141.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5874b226e90fbb3a79106534a4685e3c1e8b99d14421436ad33518099cf1a4b +size 100663296 diff --git a/params_shard_142.bin b/params_shard_142.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b4cc7b31a9bb9c0cf0cdcdc575827f20ac743b4 --- /dev/null +++ b/params_shard_142.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:882ee1796f38432ab61afac76fe703540f0cdd5385d747452152441bc3602044 +size 100663296 diff --git a/params_shard_143.bin b/params_shard_143.bin new file mode 100644 index 0000000000000000000000000000000000000000..c58f8d42f382e4e9b5c4b4e321ae22b7dbce19d9 --- /dev/null +++ b/params_shard_143.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b188a8e8eed7de66738638cb733fe3399c359e7e68e00f6ed87c5d4e176620ff +size 25165824 diff --git a/params_shard_144.bin b/params_shard_144.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ca36eed7a2fab79439741957a21aad6094d169c --- /dev/null +++ b/params_shard_144.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe6999fe225990629b6b3809c2a574ef7426cf4c122e6c2b20e3f7a1ad89f04 +size 100663296 diff --git a/params_shard_145.bin b/params_shard_145.bin new file mode 100644 index 0000000000000000000000000000000000000000..d090d015aae66eedb35b070ee1d22e5671657635 --- /dev/null +++ b/params_shard_145.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83969a18c6dcf0d32891de493fe69e1baba504a1b10bf1ae8f657c193f0f65fa +size 100663296 diff --git a/params_shard_146.bin b/params_shard_146.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b249d71d54c224dd36f3689e921ad2ea869ba2c --- /dev/null +++ b/params_shard_146.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0c427d0f0d7e354fb139d82afed24c114fa843a658d6b2ae0cd1057a00a7e0 +size 25182208 diff --git a/params_shard_147.bin b/params_shard_147.bin new file mode 100644 index 0000000000000000000000000000000000000000..1910aeebf744a18b8fe80a50b0832bead0b93fa4 --- /dev/null +++ b/params_shard_147.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab8b3ca88f3b2bae093f419fa30c11da13b9b339afcd69dffb6534083c015d2 +size 100663296 diff --git a/params_shard_148.bin b/params_shard_148.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8fc5ae846661cb582f600c7f8df3906aaac647d --- /dev/null +++ b/params_shard_148.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:468f8e7a029ec659c8b4ee602656d8c80a9a6b84f395342250527c922e77bb49 +size 41943040 diff --git a/params_shard_149.bin b/params_shard_149.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0b926d79087de2d8da40ad339fb1242a27aac59 --- /dev/null +++ b/params_shard_149.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3356cd91986d11afe332913ff336f58d61d158a62d63e65a1b1f71514ed933 +size 33554432 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0330de41d6f80f495cfaa533c041415d4f3b1d2 --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa7e2ce5352cae9da30b655db80df2be258b2004b956bb6fd2003d8ec0c8e793 +size 100663296 diff --git a/params_shard_150.bin b/params_shard_150.bin new file mode 100644 index 0000000000000000000000000000000000000000..e8f301a3d0896ab719cf86dfd236d7e300a1368b --- /dev/null +++ b/params_shard_150.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de9ad792b8a33fa058d8e2ccb670f5219ddcd2710c5561ceba8c8eb310957cb2 +size 30408704 diff --git a/params_shard_151.bin b/params_shard_151.bin new file mode 100644 index 0000000000000000000000000000000000000000..925ac8b9b92c4e30edbcb1f32baa5ebe5ff9d978 --- /dev/null +++ b/params_shard_151.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b57f4e693e8146265a9f9c68cf8c2e783559d0ba2620cbb043666b9b12bdd166 +size 100663296 diff --git a/params_shard_152.bin b/params_shard_152.bin new file mode 100644 index 0000000000000000000000000000000000000000..4a6faa31f208f5987f98d1f9791f58e851532d65 --- /dev/null +++ b/params_shard_152.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9f6b032a1fd4eb2862e9d65fd531f93728a0ddeb3935642797983e6711899f6 +size 100663296 diff --git a/params_shard_153.bin b/params_shard_153.bin new file mode 100644 index 0000000000000000000000000000000000000000..0a0ca1b859119392c516d384dd65002cf417d88b --- /dev/null +++ b/params_shard_153.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dabad14a9bf624a88622828b1875ada8fe911573f7bf5a5516df4e20e20be4fc +size 100663296 diff --git a/params_shard_154.bin b/params_shard_154.bin new file mode 100644 index 0000000000000000000000000000000000000000..793ab383360dc945559f175bc5e1ac45b2db0612 --- /dev/null +++ b/params_shard_154.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36876874746e39c2f60f786b4d64cb3c865f23f578ba33804f7998d7ca22a905 +size 29376512 diff --git a/params_shard_155.bin b/params_shard_155.bin new file mode 100644 index 0000000000000000000000000000000000000000..e24f7cc2b728ce0bd14c52a2be3eba832aabfaec --- /dev/null +++ b/params_shard_155.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f029c07650607c043b3e6ca1603dcf654f409c9d693ec2c64d9e1faa9651e260 +size 41943040 diff --git a/params_shard_156.bin b/params_shard_156.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b615bd9c8754ac18aa0ff862f5151e9c7f2056d --- /dev/null +++ b/params_shard_156.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aad904b32258823596be5a79a1f8fe8bad1d9a052640d2f758edf440c2b37c4d +size 33554432 diff --git a/params_shard_157.bin b/params_shard_157.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc43e9ceb22d0101deccac3a10c5b22ede072dde --- /dev/null +++ b/params_shard_157.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997fe48ec870ef0079cfa89091c935f92b28d920dbbdc4973b54b028f890768b +size 100663296 diff --git a/params_shard_158.bin b/params_shard_158.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ef6e276e385901c2a21fdd82e8e48f897a248ab --- /dev/null +++ b/params_shard_158.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed02dc86384b7af48f143e30804da438578a323b31c3b68d1148da783eaeda9f +size 22020096 diff --git a/params_shard_159.bin b/params_shard_159.bin new file mode 100644 index 0000000000000000000000000000000000000000..969a5f4c50fef694b9350976fea2e9680e38b81d --- /dev/null +++ b/params_shard_159.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e119888780ec2de6c3bff547c54a622a2d7ab1a114914279056529fba53c118 +size 41943040 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..80fd5b531676ea9d70dfd810f21800801e685187 --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfc111e955ecb640fbd0d0de4937f30caa0ade1bd8049b9f839e9b18b280e88 +size 22036480 diff --git a/params_shard_160.bin b/params_shard_160.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d2582b2717d002b52a1b15b5f366ea8f2b8dbce --- /dev/null +++ b/params_shard_160.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81792b57f99b8d6b8a6e2a47663280ae994554de7dea060f51fcdf02ba8bf448 +size 33554432 diff --git a/params_shard_161.bin b/params_shard_161.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0fe5fad7c303cde899829b634fd287738cb8cae --- /dev/null +++ b/params_shard_161.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1464c4af4b59ddd720afa0324df6ec81d240a97d9444925ee0724fd7292ed6cd +size 100663296 diff --git a/params_shard_162.bin b/params_shard_162.bin new file mode 100644 index 0000000000000000000000000000000000000000..2162988ef790d7fadd099b74a3b61f0bbb53f5f9 --- /dev/null +++ b/params_shard_162.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af31303f05800a96c98d58deb862d069d1ff3cda2d2419eda09e47e4c97d2696 +size 22036480 diff --git a/params_shard_163.bin b/params_shard_163.bin new file mode 100644 index 0000000000000000000000000000000000000000..92cdf8c1c0388f57deff14c9e24f66e6c37ddf50 --- /dev/null +++ b/params_shard_163.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f617e113bfd28cd2f503e41da5161755d88ad961b5ec7bab1eb11e80ea9b13f8 +size 100663296 diff --git a/params_shard_164.bin b/params_shard_164.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e716f62b417e912f897e65613e5a0a314830ed0 --- /dev/null +++ b/params_shard_164.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a1c6dd0b3a5294536860469daf782ff57cd255d8fea961b4f088be0f342736 +size 100663296 diff --git a/params_shard_165.bin b/params_shard_165.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f79be6b8766b11dc198bb3085c3cc80ad9bf890 --- /dev/null +++ b/params_shard_165.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e0da7b468ee9c29a988e509dd0c5de3e94f11ee34ac99e86145a606b879d388 +size 25182208 diff --git a/params_shard_166.bin b/params_shard_166.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d354d480c090e52d7a36c7e8c0d5acc1a6a6e53 --- /dev/null +++ b/params_shard_166.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6be02200a58ba89d302a97fc66f64dc4470522efe8003fbd8dcd83633087ad3 +size 100663296 diff --git a/params_shard_167.bin b/params_shard_167.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e9b675766b7e2a987778b79dcc18c8dba0f1bbd --- /dev/null +++ b/params_shard_167.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f1f6b40cfb039ccdee3b1d0b9486fafc92ff0252e1d9e906bb574888580de4 +size 100663296 diff --git a/params_shard_168.bin b/params_shard_168.bin new file mode 100644 index 0000000000000000000000000000000000000000..3198df095aac2fe537e2a8760be2c40b2c1c8b34 --- /dev/null +++ b/params_shard_168.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2daa8977139ccdbca11f770685756b7926d10ff922418ebcb58e7d21ee7d2306 +size 25165824 diff --git a/params_shard_169.bin b/params_shard_169.bin new file mode 100644 index 0000000000000000000000000000000000000000..48af8e3f7f03bb2dceff62c59ba03d8ddf14e413 --- /dev/null +++ b/params_shard_169.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4acc03d30e53c0635f9314f78b4a81304dd6135c7b5a9e2c9b222eee6b41d6 +size 41943040 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b967fdfef32cbfc48e1ed696da46c184cb7e374 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a588e3b3dd9b955f9068d87cdf6834571ff0246dbf50ead38108c4d579bc93 +size 100663296 diff --git a/params_shard_170.bin b/params_shard_170.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9684ac607d640e545b9a729eaf7f8984dbf949e --- /dev/null +++ b/params_shard_170.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e17f03f3ad5c5d6f5c07c1ac67f3a36834e4093f404196dcbc3b602814ea9b +size 33554432 diff --git a/params_shard_171.bin b/params_shard_171.bin new file mode 100644 index 0000000000000000000000000000000000000000..6323f7cc029e4d638c9f778bfab833fa5c92eace --- /dev/null +++ b/params_shard_171.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f59d5918ada79d49c0652d05792e3e873995df0ddcd3f86ed31c28938857df0 +size 100663296 diff --git a/params_shard_172.bin b/params_shard_172.bin new file mode 100644 index 0000000000000000000000000000000000000000..68ded7ad85a4592085957749c1fe47005f46dfc5 --- /dev/null +++ b/params_shard_172.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b77ea80ee15c12c0859236df82dc2243b6a4ac8ce63d0445de023888cb32416 +size 22036480 diff --git a/params_shard_173.bin b/params_shard_173.bin new file mode 100644 index 0000000000000000000000000000000000000000..2eeedd07f534861be09fccdbb18ad20b6b3264ad --- /dev/null +++ b/params_shard_173.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20dad908f457c7a8b766210c7a79916d85467c56afbe7d116c9ed5493bd9599 +size 100663296 diff --git a/params_shard_174.bin b/params_shard_174.bin new file mode 100644 index 0000000000000000000000000000000000000000..1342999c5ed33edd2e65395541a830cf41a56390 --- /dev/null +++ b/params_shard_174.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9151466d50bfc2c7ea5177b01827c28f226dcda09b49a35ae9d9d5f43abe715d +size 100663296 diff --git a/params_shard_175.bin b/params_shard_175.bin new file mode 100644 index 0000000000000000000000000000000000000000..b06c45a08054c2e06946d315d14674ac597b211f --- /dev/null +++ b/params_shard_175.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a6e7c3fa4d634a522eb9135e264a738be13a8a2e85d41b74b60d5f8618411b +size 25165824 diff --git a/params_shard_176.bin b/params_shard_176.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b85a17d9e503bde7e1b9b47b3829f65761f2bdf --- /dev/null +++ b/params_shard_176.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9bf669d7b979d3f8c9b0300ca92ef1a848750a1a07466492292a4b25c3a9e19 +size 41943040 diff --git a/params_shard_177.bin b/params_shard_177.bin new file mode 100644 index 0000000000000000000000000000000000000000..0bf826b2916c41bdc7ae29ebd115df059e2dbbd0 --- /dev/null +++ b/params_shard_177.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1429bc999c8f0ff72e576fb6582fdaa462c7f14655ea8a1758a858d947b51e3 +size 33554432 diff --git a/params_shard_178.bin b/params_shard_178.bin new file mode 100644 index 0000000000000000000000000000000000000000..baf9cbe8b0634162e2099a61e1fff55e317a8b50 --- /dev/null +++ b/params_shard_178.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9234777649650c33fe320615912a0bf03b76a5205ca0e1e0f5f61974ae34f5 +size 100663296 diff --git a/params_shard_179.bin b/params_shard_179.bin new file mode 100644 index 0000000000000000000000000000000000000000..98f343564030cb81ded23b607b39d3d7188efe5d --- /dev/null +++ b/params_shard_179.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d9b2e8fa1cdf090eb8be9b1cb54f24565bd9853b11edd0dd1f17b834ac9ba39 +size 22020096 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..3152ed2d9a8f6eb8547018752aca150b926149d5 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72ab0691d2175c93e7c913bb257eddcc89c924c2efc37398a889277ebc32c0c +size 100663296 diff --git a/params_shard_180.bin b/params_shard_180.bin new file mode 100644 index 0000000000000000000000000000000000000000..d909adb9dcf874ee650fc71a9ef71e6b735860d6 --- /dev/null +++ b/params_shard_180.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84be971ed052a5a466bdb2e9e8426f533ee17c78d6bfc0215347cdd1d7666b7d +size 100663296 diff --git a/params_shard_181.bin b/params_shard_181.bin new file mode 100644 index 0000000000000000000000000000000000000000..0106d2d2ab6d668a217294b65f107c8350cf7a01 --- /dev/null +++ b/params_shard_181.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b91c7922857a87360b116dc2d062f4ebc46b70f0ef3b5ee515834738709fec +size 41943040 diff --git a/params_shard_182.bin b/params_shard_182.bin new file mode 100644 index 0000000000000000000000000000000000000000..424b6d1e50035816fb164f09fb667761aa7540e3 --- /dev/null +++ b/params_shard_182.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c155589ad402530591436e6a44e583a9726dd8272851491c77c149a00776c1 +size 33554432 diff --git a/params_shard_183.bin b/params_shard_183.bin new file mode 100644 index 0000000000000000000000000000000000000000..c4769c31590d6e74a4af89fd0290ac740027cb7c --- /dev/null +++ b/params_shard_183.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e16b8c8feebe6db24b53754868e2b98fa56d0b99c33324204734871e8cfe19 +size 30408704 diff --git a/params_shard_184.bin b/params_shard_184.bin new file mode 100644 index 0000000000000000000000000000000000000000..474506be0e7ede7be3d4504d6b407db199093374 --- /dev/null +++ b/params_shard_184.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22754f54f4ee660b4e8e28a946289abac5329a4f8b42aef84397509a3670029 +size 100663296 diff --git a/params_shard_185.bin b/params_shard_185.bin new file mode 100644 index 0000000000000000000000000000000000000000..b70c1ca8b6cf9c311f5e41962da06f34b8eb2321 --- /dev/null +++ b/params_shard_185.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c13fb18ee3b10ef30cfdc02bea059fcaf6a03e8d81c370626dca2af403fca604 +size 100663296 diff --git a/params_shard_186.bin b/params_shard_186.bin new file mode 100644 index 0000000000000000000000000000000000000000..739ef60ac80f685cc887c2798ea56d581ddeb702 --- /dev/null +++ b/params_shard_186.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6c86afba7206cc5520fe5f2fe2de822f60469cdf9bf2159e01c42c59413143 +size 100663296 diff --git a/params_shard_187.bin b/params_shard_187.bin new file mode 100644 index 0000000000000000000000000000000000000000..94aa2357585de0c4e808c79b383e698450a46993 --- /dev/null +++ b/params_shard_187.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c624fe8c71a70410c9fcdf00c62a16ec6c962bc3ad3823e7374a735e4379a60b +size 29392896 diff --git a/params_shard_188.bin b/params_shard_188.bin new file mode 100644 index 0000000000000000000000000000000000000000..044cc9620fa0b0cc109b44ba5df865f9ca21531f --- /dev/null +++ b/params_shard_188.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e290b7da6818a19439a1cc4be9f2db544da32c7515b91165cbe2425a6cabde +size 100663296 diff --git a/params_shard_189.bin b/params_shard_189.bin new file mode 100644 index 0000000000000000000000000000000000000000..c27fee9af57f396e3b62bd9e67a3ab291242ba38 --- /dev/null +++ b/params_shard_189.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb1f567ebeb5cd937686993b22bbe58c9815f05e23302a8ab97ab9f28d661af3 +size 41943040 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd40fab3d79f684bbac38c67f82dd4419267b199 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae9c22947110292584e01c2773fc5619e05bf9fa84280eda969efea01100a84 +size 25165824 diff --git a/params_shard_190.bin b/params_shard_190.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ba2853a8fa25cf342d0b2c03852230d756a856b --- /dev/null +++ b/params_shard_190.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dce6bdc7014c2458820cb921f446010b97792f1b1c333a5f0d532d257739868 +size 33554432 diff --git a/params_shard_191.bin b/params_shard_191.bin new file mode 100644 index 0000000000000000000000000000000000000000..456c6d1b306d4ac3f301ca55e12b2a0329327e9b --- /dev/null +++ b/params_shard_191.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded8bb180de6acad05241a019cb3d03045db547ee28839b0437e5a834e35b39b +size 30408704 diff --git a/params_shard_192.bin b/params_shard_192.bin new file mode 100644 index 0000000000000000000000000000000000000000..b121f0b66ff385d9b665ee2918938cd356117d38 --- /dev/null +++ b/params_shard_192.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5993500ca1fb556bbc1665b866de9a69ef27c6a381895f91b00be64a322d61 +size 100663296 diff --git a/params_shard_193.bin b/params_shard_193.bin new file mode 100644 index 0000000000000000000000000000000000000000..75d79a4ed1e506706f4b0a59b3c853e4aef33c3d --- /dev/null +++ b/params_shard_193.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363ced3485bb6d3e6eb32cce16b5260795b3b5e24338506c9233c48cba444dc7 +size 100663296 diff --git a/params_shard_194.bin b/params_shard_194.bin new file mode 100644 index 0000000000000000000000000000000000000000..69cedeae335940ed1c26a20ac0f743fecb04f7eb --- /dev/null +++ b/params_shard_194.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fbef78b47ffa7f20027bbe7300cce966059868764ed579e97312c5895f2252f +size 100663296 diff --git a/params_shard_195.bin b/params_shard_195.bin new file mode 100644 index 0000000000000000000000000000000000000000..102f217137fa212fc530d563b7d2bf162cd931c9 --- /dev/null +++ b/params_shard_195.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd4878f1b41aaeb9073820e99c60976c7f942aab0632836a4bf6d6b0b73d765b +size 29376512 diff --git a/params_shard_196.bin b/params_shard_196.bin new file mode 100644 index 0000000000000000000000000000000000000000..b30e20036a728ae0625bddf55dc2eb00dfbd4610 --- /dev/null +++ b/params_shard_196.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea8afddb439e05f16b1541fb2d5516ebb06349b2f373fc09588af8f307d25d0 +size 41943040 diff --git a/params_shard_197.bin b/params_shard_197.bin new file mode 100644 index 0000000000000000000000000000000000000000..524ce4c9450116fbe85fab84218d8a1430b8d35b --- /dev/null +++ b/params_shard_197.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dda1cb39da1681e3760d507bed9e5a451e481eb3e4331685ae30cd0b40ba5a4 +size 33554432 diff --git a/params_shard_198.bin b/params_shard_198.bin new file mode 100644 index 0000000000000000000000000000000000000000..cac0cadc93063f8c22b45c4ee1a1b66c20a90d49 --- /dev/null +++ b/params_shard_198.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:842b1f9245264aa23b0699a64fed39884072817b2eebff80ce0c9975f98f3a36 +size 100663296 diff --git a/params_shard_199.bin b/params_shard_199.bin new file mode 100644 index 0000000000000000000000000000000000000000..cef1447a1b611315b8f59190eb6e0adb5af4d14a --- /dev/null +++ b/params_shard_199.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b733ff4cbbf2e09580440dca8d39912220d3cee445fc686212289539ab0eba5 +size 22036480 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..4148f251bc94e8aa66fc549e6c9c4cc1e7ea1c95 --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1eab7a780c293cfb56e9058fa7ce9c080ad70ff6bf8c2934434cc4e89b3d42d +size 100663296 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..47b200b698d8118718a7c672bb3a7f6a41ae59cd --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86203fbef0e14829ecb2369cc6f307cb7a35ee2dfc0feef0e0f8b08647e54804 +size 41943040 diff --git a/params_shard_200.bin b/params_shard_200.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f11ea5815b93153a822364a0ee5c46c44e33ef4 --- /dev/null +++ b/params_shard_200.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf526e36b733c4927becba1110d3fbcc605e89793a944a5307e5c5b7da4aa7fe +size 100663296 diff --git a/params_shard_201.bin b/params_shard_201.bin new file mode 100644 index 0000000000000000000000000000000000000000..29f2e8bbbe7b28138f786d1254620dc0a7060296 --- /dev/null +++ b/params_shard_201.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a342a602f3c1a7785ffaa2b7405f4990a2139ae2975cba813c060527ccf4f0b7 +size 100663296 diff --git a/params_shard_202.bin b/params_shard_202.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f77f281ef20f5fd888ef07bb6c3c82d70fbb213 --- /dev/null +++ b/params_shard_202.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7089e55988a8aff0acd2a48affa1a4b1f1209bb4061c24a3be39721d0e6fc7ae +size 25165824 diff --git a/params_shard_203.bin b/params_shard_203.bin new file mode 100644 index 0000000000000000000000000000000000000000..83d2fed6033033dcd272f68bfe2d9748168a4586 --- /dev/null +++ b/params_shard_203.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c04e8dbf6404e9f9a6b392374bbc19ffdad39fda88b9e54e41e4d9ea25791a1 +size 41943040 diff --git a/params_shard_204.bin b/params_shard_204.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d0a112037b4bf6cd8d46de2d3b44f7745c620c2 --- /dev/null +++ b/params_shard_204.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3af11a1fca4f5ba44defff280aa3c80d483f58e6cd36cf76a194c91272dac5c +size 33554432 diff --git a/params_shard_205.bin b/params_shard_205.bin new file mode 100644 index 0000000000000000000000000000000000000000..e28ddd6621ff854dd9a132b152b178ca305edc5f --- /dev/null +++ b/params_shard_205.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9728546b805e7aab3f3b65b1d8546bb8b8174d2bf09c70580d0b2f42e36c9cf5 +size 100663296 diff --git a/params_shard_206.bin b/params_shard_206.bin new file mode 100644 index 0000000000000000000000000000000000000000..be2b16caccfc572810cee92674da7589b21bd3cc --- /dev/null +++ b/params_shard_206.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c171f8259d565cce8b92ba944572726230ceddb4c5429ea909bfe676ee29ff +size 22036480 diff --git a/params_shard_207.bin b/params_shard_207.bin new file mode 100644 index 0000000000000000000000000000000000000000..26b997b5b0e7a124845c745f5149fc767565080e --- /dev/null +++ b/params_shard_207.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e01285855a4efd34c6a4090f3e2eeff71900a106f4902662cf3bb0fb2c01324 +size 100663296 diff --git a/params_shard_208.bin b/params_shard_208.bin new file mode 100644 index 0000000000000000000000000000000000000000..df0491cc721b45b0dce099e46829ff4800f80e39 --- /dev/null +++ b/params_shard_208.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b79063f748be1efd2f52b68abcf6d6dd4fdcc9e280bc2801c9a53868fb6a9ad +size 100663296 diff --git a/params_shard_209.bin b/params_shard_209.bin new file mode 100644 index 0000000000000000000000000000000000000000..5cb499709a4e2c77c866a0fbebc6cbd0c103da88 --- /dev/null +++ b/params_shard_209.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e562853a1ea2b9430b83ba348f57600fa7c47dae53c6e59550bea83dca9488 +size 25182208 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..97d31d84cf26b928d7a6590ded09b3e16af9586d --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa45b20f41340b03602e9077412153a37bf440fbd9dea3bf5c6db423d8e3e96 +size 33554432 diff --git a/params_shard_210.bin b/params_shard_210.bin new file mode 100644 index 0000000000000000000000000000000000000000..a5d7514f03ace95b65382b2202788acea58ad97f --- /dev/null +++ b/params_shard_210.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96884142a8bb1f6cb7654e673dc2c4b521f47fc70f83c4d58267fd74fb604b6 +size 100663296 diff --git a/params_shard_211.bin b/params_shard_211.bin new file mode 100644 index 0000000000000000000000000000000000000000..d4273fe7a1ef9048189232521c470edaa065affc --- /dev/null +++ b/params_shard_211.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345ca753f55b116120c7e7ede3ff562552ed7b736fa2654edf985c4ce7cb9dfc +size 41943040 diff --git a/params_shard_212.bin b/params_shard_212.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a013043ad62e81a3d077644fe38f554babb8b2d --- /dev/null +++ b/params_shard_212.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07193d063cdb3c877ba39b3a7a71c27cd2fb037efe363f2b570c7489384f70b +size 33554432 diff --git a/params_shard_213.bin b/params_shard_213.bin new file mode 100644 index 0000000000000000000000000000000000000000..755a8773b8ec4d957c59e3593489d8c8fdddc9c4 --- /dev/null +++ b/params_shard_213.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9008248dd32d37994843775d41cf146157238b9027389a0aef1dc51d7ded502 +size 30408704 diff --git a/params_shard_214.bin b/params_shard_214.bin new file mode 100644 index 0000000000000000000000000000000000000000..0485c0da9dc92c6a4fd85dfb24074c1a8f858985 --- /dev/null +++ b/params_shard_214.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71ef2d0dbe71f90d14d30492320fb0ba381cbd7accdf37ffd1c5288cec5b93ca +size 100663296 diff --git a/params_shard_215.bin b/params_shard_215.bin new file mode 100644 index 0000000000000000000000000000000000000000..44bad87a440c931a245d7efe2c3fcdb70df1018c --- /dev/null +++ b/params_shard_215.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2896e34b2247f799a78454e32e51d3739ccae43740dc59a2e68b0cdcbefa14 +size 100663296 diff --git a/params_shard_216.bin b/params_shard_216.bin new file mode 100644 index 0000000000000000000000000000000000000000..f7385126f5871c73379c1669d7c7870ef65edc13 --- /dev/null +++ b/params_shard_216.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1488572abdc9bdf97cbbe791183c6dc9d551b50a303e4a8680daf9227e5b1ec5 +size 100663296 diff --git a/params_shard_217.bin b/params_shard_217.bin new file mode 100644 index 0000000000000000000000000000000000000000..a33080dc4b94829fa011b1ff71ce81a7a8a10ce8 --- /dev/null +++ b/params_shard_217.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e71feacc1482a1a49812a92abdf966a50223ed9ef788d31cd38615834fffcd +size 29376512 diff --git a/params_shard_218.bin b/params_shard_218.bin new file mode 100644 index 0000000000000000000000000000000000000000..7bd14ec475718a4d5ab285ccb147369156369443 --- /dev/null +++ b/params_shard_218.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84c6f882bac6c72165074eb6b4df928e0955285122bec9a0758d52fc4326a422 +size 41943040 diff --git a/params_shard_219.bin b/params_shard_219.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c8a59eda5a63691594781a6d91bbf6e613c2e8f --- /dev/null +++ b/params_shard_219.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94854469e6b19b16108981f926715bbbe67aff2c65002c87079d95f81954517e +size 33554432 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8f9fb67944541ddbc4f7cbe6157eabdfc91e2e3 --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48c1440ea756758ae3c8d5b306f97beedbb925e8e8a33457b22d1bff0e88ae9 +size 100663296 diff --git a/params_shard_220.bin b/params_shard_220.bin new file mode 100644 index 0000000000000000000000000000000000000000..8161158f60c62e839b1abfa6057461da2bbaf806 --- /dev/null +++ b/params_shard_220.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d0907063baeb8adcf380704b2ef9874d0dabc66464b5254609297ee5fccfc0 +size 100663296 diff --git a/params_shard_221.bin b/params_shard_221.bin new file mode 100644 index 0000000000000000000000000000000000000000..60850360c36e857a1413a511b9caf3c1774242c7 --- /dev/null +++ b/params_shard_221.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b51b37b26163c11cc130cca227d5f33507f5180bf14fd11198d7725f589894 +size 22036480 diff --git a/params_shard_222.bin b/params_shard_222.bin new file mode 100644 index 0000000000000000000000000000000000000000..8856151c32976b794cb2bdb2881c8101a1112e13 --- /dev/null +++ b/params_shard_222.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1accf556b64424a8a5f49f4855fb1b675c4828293e0b3be2a78f6934839769a7 +size 100663296 diff --git a/params_shard_223.bin b/params_shard_223.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a98a6213c422f00fa858588bacd85461c1f762a --- /dev/null +++ b/params_shard_223.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34239a9cc0a4ab3a3a47a87b82381d45fe5e571d75375cd18d2dc7338e0e9d92 +size 100663296 diff --git a/params_shard_224.bin b/params_shard_224.bin new file mode 100644 index 0000000000000000000000000000000000000000..21d6cf86358489515501486e6df24b1e4a7887b9 --- /dev/null +++ b/params_shard_224.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109691f125393c115605f9afa59ad3f132e0fac4ee815902faeebe81192b040a +size 25165824 diff --git a/params_shard_225.bin b/params_shard_225.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5ac71bb261ef16ed64d1ec016bd34ee3d1d9dfe --- /dev/null +++ b/params_shard_225.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baf28810755eeed4c076797884bd875c3d72e42e9f6d4f5483ae9789e19da8b1 +size 41943040 diff --git a/params_shard_226.bin b/params_shard_226.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ee79bbbfe6b7d01ee5055ca265593c202f451f9 --- /dev/null +++ b/params_shard_226.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b8de2b8ea52e88dddbd7ef2973f028e90b3567cd0ab269e5d320e19eb9a808 +size 33554432 diff --git a/params_shard_227.bin b/params_shard_227.bin new file mode 100644 index 0000000000000000000000000000000000000000..352713219bad96ff019ce4f2b9cc79bd23aed3c9 --- /dev/null +++ b/params_shard_227.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a7f0a92f9a88162dfbc6225cb6b1445ce64adf777e8be0d61d24df76b625571 +size 100663296 diff --git a/params_shard_228.bin b/params_shard_228.bin new file mode 100644 index 0000000000000000000000000000000000000000..871e44aab6c8a4c26c711bdefe4738332761b525 --- /dev/null +++ b/params_shard_228.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8b3a91e185d3456a1531a1aafe2a6a7d70d03cf969482744b35bdcab738ac2 +size 22036480 diff --git a/params_shard_229.bin b/params_shard_229.bin new file mode 100644 index 0000000000000000000000000000000000000000..ae6981d4ca450f83b442d99ef9af32b3f7aaa31c --- /dev/null +++ b/params_shard_229.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6e82ea25a0eb53c58ad372d3558e811d5c5fb497ad9d3c2b502c73c87df757 +size 100663296 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..5873b6d83825e76aa7f45989d4f11a3a6059fccb --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:130db8da0f010bf8b4abfa55d1609d488a3ce4ee6d0623e41e2fb1d14d06c827 +size 22020096 diff --git a/params_shard_230.bin b/params_shard_230.bin new file mode 100644 index 0000000000000000000000000000000000000000..106f9402b4a54bee70929e3d0e859865e2a5d44f --- /dev/null +++ b/params_shard_230.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c8cbff8ad6d2c67c3e0cd6ac1a2c339ad963a7f8e8af9ee94b7b8ca58605ae +size 100663296 diff --git a/params_shard_231.bin b/params_shard_231.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d993b9d910001dcc6d9203062c20959c63baa3d --- /dev/null +++ b/params_shard_231.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:116698fca2eaf529f0b2c7bd35985285abd810d3afd7342dca4d4b1094142b14 +size 25165824 diff --git a/params_shard_232.bin b/params_shard_232.bin new file mode 100644 index 0000000000000000000000000000000000000000..0450db44a63da83db0134129d477880af3e613f6 --- /dev/null +++ b/params_shard_232.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96818f256f3517bda5260bcb186657c731a6176131ad6daa0868dbd3b43344d +size 41943040 diff --git a/params_shard_233.bin b/params_shard_233.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d02978fdca9bfb4831126f7721db9184d708711 --- /dev/null +++ b/params_shard_233.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79793ac43a5f9168b0669be0030e05aef0a42ebbb3d2f5a6a503609ebe6a5a04 +size 33554432 diff --git a/params_shard_234.bin b/params_shard_234.bin new file mode 100644 index 0000000000000000000000000000000000000000..cf044037c7f2712a7358f887f5e61ed567814f86 --- /dev/null +++ b/params_shard_234.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b656f17875e22ce38dd6b5026e67cad32094c9e8f20d5ef12b41fb60463b1e9a +size 100663296 diff --git a/params_shard_235.bin b/params_shard_235.bin new file mode 100644 index 0000000000000000000000000000000000000000..75973d9a75708435ccdb3323e55015d77a361844 --- /dev/null +++ b/params_shard_235.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54018e53a984b8aadc9084c715ac3422e0f560ce084b89b693ae7fbcbfe0131a +size 22036480 diff --git a/params_shard_236.bin b/params_shard_236.bin new file mode 100644 index 0000000000000000000000000000000000000000..b369237c1e5e07e44a9e4fb0b1dbad7cf2d78477 --- /dev/null +++ b/params_shard_236.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048481c119e930efff0b8378ea1ee9382052ed34b21010a3e21edff929121aea +size 100663296 diff --git a/params_shard_237.bin b/params_shard_237.bin new file mode 100644 index 0000000000000000000000000000000000000000..32f902bbefdf9e38c9f88fc2ddc334fddf357d65 --- /dev/null +++ b/params_shard_237.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6dbf7edb6b79f9ded502e3d7f3612c3d8778ee1eedf1b7de20ef6478d73ff0c +size 100663296 diff --git a/params_shard_238.bin b/params_shard_238.bin new file mode 100644 index 0000000000000000000000000000000000000000..d49e34cb8d82f48f3de3812f65b582ddedca96f0 --- /dev/null +++ b/params_shard_238.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa462124774df953c5474f001d5a1224f0d7d909d8644c90f675a195b094159 +size 25165824 diff --git a/params_shard_239.bin b/params_shard_239.bin new file mode 100644 index 0000000000000000000000000000000000000000..50a34b7b71697d4b9d1d1a4cabc9734451354d53 --- /dev/null +++ b/params_shard_239.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae4a27c9d73870be252fddfbba30867b93224d8cb7ec755abc71eeff5a54dd7 +size 41943040 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..37e029519770e254d6640716cafdfb0c424bc40b --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79755205b696773561d9337214b59d0a975dbb07c718885a984f45f92b9682d2 +size 100663296 diff --git a/params_shard_240.bin b/params_shard_240.bin new file mode 100644 index 0000000000000000000000000000000000000000..245f0d35d22b168db580d220712dc8976c06ad55 --- /dev/null +++ b/params_shard_240.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb187dd82b38ce3d963ce6fd5f42fddb7fc54c6ee002352e391c2ec8eb3d65d7 +size 33554432 diff --git a/params_shard_241.bin b/params_shard_241.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c546fa25b6039c725622b8908b2923b6e6b6fb3 --- /dev/null +++ b/params_shard_241.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83dfb389eb11c6922ec41d3adde3664a1362f4aaf38e8fdcdd76c1fa848b3dc3 +size 100663296 diff --git a/params_shard_242.bin b/params_shard_242.bin new file mode 100644 index 0000000000000000000000000000000000000000..5ee91a5c527602c4f565c3f848c6693020faed7d --- /dev/null +++ b/params_shard_242.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2588713ce2bf96848b3435a21b47ab693fb3a9eedeec7eafdbc67f3b4b9f060c +size 22036480 diff --git a/params_shard_243.bin b/params_shard_243.bin new file mode 100644 index 0000000000000000000000000000000000000000..46f9158b92d9daea4d70b16d4b57dd7c0b19f9ba --- /dev/null +++ b/params_shard_243.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e72c3b57b2a444ba82212eed87a4f12e3a74e75261501f902a9b6750f46b71 +size 100663296 diff --git a/params_shard_244.bin b/params_shard_244.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c6b76bdc56a8a9b2d8612c2e3229daf0dadaa11 --- /dev/null +++ b/params_shard_244.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5581f9da6c2a08c6d4385caae7bf93f2c1b36cdd0e8cded3531f3c356ef193a7 +size 100663296 diff --git a/params_shard_245.bin b/params_shard_245.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d4e40491e638ef2fdd8ea8c5f248ba2afddec06 --- /dev/null +++ b/params_shard_245.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf9c3c6b926483dd44b58fbf0f7245831a561fd4c8fc679018a2dd961dc3924 +size 25165824 diff --git a/params_shard_246.bin b/params_shard_246.bin new file mode 100644 index 0000000000000000000000000000000000000000..374b0ef70f7931e97a18d26b43cb9748dc2222b5 --- /dev/null +++ b/params_shard_246.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d260874c9f443930d093efc5d80df516a270481168ee692b64aed2a62f2eb26 +size 41943040 diff --git a/params_shard_247.bin b/params_shard_247.bin new file mode 100644 index 0000000000000000000000000000000000000000..bfb52d8711ed87d78b42a828a6cacf5ce0f391e9 --- /dev/null +++ b/params_shard_247.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d94e9a04fed22c52503410444599efa240e99809d2f6479947ee7389fef0bc +size 33554432 diff --git a/params_shard_248.bin b/params_shard_248.bin new file mode 100644 index 0000000000000000000000000000000000000000..20513abd386d3b97a931ddd0e599a178fa39f071 --- /dev/null +++ b/params_shard_248.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b449030d93562986a31655d1223b6a9310fc567dcafede244a7303ae70aa4e +size 41943040 diff --git a/params_shard_249.bin b/params_shard_249.bin new file mode 100644 index 0000000000000000000000000000000000000000..a10ce7e01e176cea96d0f560a32a519bf4254a6e --- /dev/null +++ b/params_shard_249.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd47870a559a947c4227c1df5bb3c6afa8306c7e169aff0dfe46705c8f9b2fa +size 33554432 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..cdb7a39323c58da12f06f59d4ea6887905835ca4 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93fc4a2bd04e5a66dbfe8d12dcda70440c5eeee0542eee4cb3606afab97bbe08 +size 41943040 diff --git a/params_shard_250.bin b/params_shard_250.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6288c7ed03871cbd77d28a72220dfc80ee7c51f --- /dev/null +++ b/params_shard_250.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fbd6d59173293206a794d939b63935bc619303bd22064623012f28cc368e626 +size 100663296 diff --git a/params_shard_251.bin b/params_shard_251.bin new file mode 100644 index 0000000000000000000000000000000000000000..c04190973050cd8daea3c5c5e796c4b7d5c0bbad --- /dev/null +++ b/params_shard_251.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea49e5b015bfaa0e5666164102bf9f05af734bcda1f0a5f9c42397f98e4da587 +size 31473664 diff --git a/params_shard_252.bin b/params_shard_252.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc45b9bcd29ca5b22f06e46fca19d9b22a903577 --- /dev/null +++ b/params_shard_252.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d52066354c7cc685fff07ad95de63bc5ad49805c47a1a3a4ce1bca3a85116160 +size 100663296 diff --git a/params_shard_253.bin b/params_shard_253.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef00f6b3b3aac6d726ee866567da02d9d88ac9dd --- /dev/null +++ b/params_shard_253.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9ff168f27637a961f176c48a72cf5537dbbf78a8c713af49697dfecb0547c6 +size 100663296 diff --git a/params_shard_254.bin b/params_shard_254.bin new file mode 100644 index 0000000000000000000000000000000000000000..20a6237c9b949cd1d706ba89503ad4a2585d72a4 --- /dev/null +++ b/params_shard_254.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8314f457bd214a5f11ef83d32c32c05bdb9995ce9f62d683be113a73b499743f +size 25165824 diff --git a/params_shard_255.bin b/params_shard_255.bin new file mode 100644 index 0000000000000000000000000000000000000000..7e5ed057ce12331e9498ccbae226cc4af0e95e99 --- /dev/null +++ b/params_shard_255.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c10dd20424669fa9642e18b4ee6e302fdf6a87d24c815ef34cb7954dd2ec92 +size 100663296 diff --git a/params_shard_256.bin b/params_shard_256.bin new file mode 100644 index 0000000000000000000000000000000000000000..008e880b747e7edefd98056b7761f89ec30260b6 --- /dev/null +++ b/params_shard_256.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b2929238c4185abcbd98836f97c23f860291edf5df6f3d8aff1b8d05d3d748e +size 100663296 diff --git a/params_shard_257.bin b/params_shard_257.bin new file mode 100644 index 0000000000000000000000000000000000000000..2cc5aa60e0fbfc5263e1bd471f5c62204aa2ab39 --- /dev/null +++ b/params_shard_257.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13b7e1bdceae5c66d9be38782aaa6e6db80b58dc325403265d52eb01002a1b4 +size 25182208 diff --git a/params_shard_258.bin b/params_shard_258.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ea7034fb069d2cbdb9f9c51383284189d05e3d2 --- /dev/null +++ b/params_shard_258.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da1504d3fc1140935efe3e6cf7e5e4a45d56ed8850b51dc07a615b32d7ff38e3 +size 100663296 diff --git a/params_shard_259.bin b/params_shard_259.bin new file mode 100644 index 0000000000000000000000000000000000000000..23bf2d66d7975bb2c205bb71d088325f2230f7b4 --- /dev/null +++ b/params_shard_259.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee89022e4d1ce1c8371519746b3e13f2e43ec0f41b0af7ca3cb90a02ed7e650 +size 41943040 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac3f9f3f2053d21c93b3bbbfc64a01761c92b95c --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5cdd65b2f35743bada335ae33ae3877a527afa2e79a22291b2efff31b2281f +size 33554432 diff --git a/params_shard_260.bin b/params_shard_260.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b3d9426ccc45fcefe2d836e6b8087a9434b9f79 --- /dev/null +++ b/params_shard_260.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a5e190ce932f35d6be597a4975c0823be4d322289ad05b9047907d7029dcff3 +size 33554432 diff --git a/params_shard_261.bin b/params_shard_261.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b2cf52adfb46c957fc0a892c452cfdf6fc55707 --- /dev/null +++ b/params_shard_261.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b45e6eaebb9d98ee9ce8c13127cc0e8dcb695975240602a4e9405c415b628a7b +size 30408704 diff --git a/params_shard_262.bin b/params_shard_262.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e39ef7126897bba63a15fc2ff60e978a96d69ca --- /dev/null +++ b/params_shard_262.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4c4a1fd7519a4684c9dab0adbc745fd315771ddfe834bfc701690f7ec4f260 +size 100663296 diff --git a/params_shard_263.bin b/params_shard_263.bin new file mode 100644 index 0000000000000000000000000000000000000000..c6053320f9b4debda37380cf8b46f3fca3acf261 --- /dev/null +++ b/params_shard_263.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c70d3002f94861d991e8fe47ebacb4b15471db827edf89fb1cc5c11b4c9c28a +size 100663296 diff --git a/params_shard_264.bin b/params_shard_264.bin new file mode 100644 index 0000000000000000000000000000000000000000..911c2ae89c2752045c80e55137ffa822039f1182 --- /dev/null +++ b/params_shard_264.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a924e2e9f396f9052049b2c420d7678f50a66867c7b65fcc69689684c891f47 +size 100663296 diff --git a/params_shard_265.bin b/params_shard_265.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef5434030e00da5f8c3641659f6e6373ca8ee691 --- /dev/null +++ b/params_shard_265.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ef06cc4e4e7ae6f348a01625ce87c746759d853ba3f1bd9937bee6046b6a16 +size 29376512 diff --git a/params_shard_266.bin b/params_shard_266.bin new file mode 100644 index 0000000000000000000000000000000000000000..b09abc1a2e59fbc7f2c7664bacee3ff343200b15 --- /dev/null +++ b/params_shard_266.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b92369372e6baf3a12d1d7371c46b623cc33dcfc4fe7b0737ea24f22aa990f +size 41943040 diff --git a/params_shard_267.bin b/params_shard_267.bin new file mode 100644 index 0000000000000000000000000000000000000000..e35ca26ede8f0fe38945e131ff7dfca36790f8b0 --- /dev/null +++ b/params_shard_267.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b43c78e8298c49804d4fb792c7cbe579b77f05157e0261b60a15642f6909b4 +size 33554432 diff --git a/params_shard_268.bin b/params_shard_268.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f70a280a82dd0570acb336f7cdcd01874b2c291 --- /dev/null +++ b/params_shard_268.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eae0343080fc229e885129f4ef74181d9a9374e2c4fefc5610b03c5d3d9e2b0d +size 100663296 diff --git a/params_shard_269.bin b/params_shard_269.bin new file mode 100644 index 0000000000000000000000000000000000000000..e30b965b4e31d3a821aa311daed72c4e01f0a266 --- /dev/null +++ b/params_shard_269.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac03ed8a5d51220c76053dfc3e7f98cc0abf27199de2902573987117bd394db8 +size 22020096 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..638343bb53b3ccd4526e09cc9528eea30da2d8c1 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:270177b2e9bdb55a538b743b1fdc410b44efa1c09bff2b3a982ddbeea3037b6b +size 30408704 diff --git a/params_shard_270.bin b/params_shard_270.bin new file mode 100644 index 0000000000000000000000000000000000000000..65969d8ae9c44cdcc2adb70dbdcc1b8055e3a0ff --- /dev/null +++ b/params_shard_270.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6d984b323c26317f156413d6329538cf93559367e8c46a7c50c98feec619d3 +size 41943040 diff --git a/params_shard_271.bin b/params_shard_271.bin new file mode 100644 index 0000000000000000000000000000000000000000..7cc5e822fca77f5f4be93e4504cb095cfa3aedcc --- /dev/null +++ b/params_shard_271.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:510e75549d7c37bcb71a412d9b24e82f0a68e5a8151420b4d13e2277fa28a17e +size 33554432 diff --git a/params_shard_272.bin b/params_shard_272.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab41ee48d1b76f1321b755083e9e2f10625fbe2b --- /dev/null +++ b/params_shard_272.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c72619892ed2bfe3bbcebebdcbf032b6c44ebb40c7047bcf0988dc8b5c0cb775 +size 100663296 diff --git a/params_shard_273.bin b/params_shard_273.bin new file mode 100644 index 0000000000000000000000000000000000000000..96bb32c06b51df73767bf959091f2d1655e92f80 --- /dev/null +++ b/params_shard_273.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d405ecd6d0ed22f7549245d73692ee9d6584c1a64dfc03a5a1f5172053df659 +size 22036480 diff --git a/params_shard_274.bin b/params_shard_274.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef28be16ac7e462f28e51106f8d696365f4e21f0 --- /dev/null +++ b/params_shard_274.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:755ec5a2fdd9ae0e7618e453c0ab4d9c0b6e0af083153adf3e04b34e335b9a2c +size 100663296 diff --git a/params_shard_275.bin b/params_shard_275.bin new file mode 100644 index 0000000000000000000000000000000000000000..0c8911116fd4d69450938635b380841e9b053925 --- /dev/null +++ b/params_shard_275.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d571bbeba32eaa4af22c00f477ce4607ff1cd2f8b3621fb5182eaa60b6967c53 +size 25182208 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..1df8317928c2ed581b23b92fb65cee99ac120320 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd4a6957af8bc540611c6e49ee68a72eda6649896ad23a28fa2aadf86036ca56 +size 100663296 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..0efbb11545d650cac04a7058394badd5b47583e4 --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1dc3d2f4e01666fc99e6ad38e646ab62d7d31316ce5f0af4b374e6ce9367cdd +size 100663296 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..8abd41ec69abbe28490a7e32171ab1193d5dd1bd --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80acc187215746b7368a831cd3c4dddacd5d10b11e9759f8452c5ed052cd4d62 +size 41943040 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..c5b3fb8b613ddd965cf5c114434cd8ff26c85075 --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d365c5911274e0498a422093ca7899729d8bb1229a5d4d4da7c59197ff06aad +size 100663296 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..c75cc883739fdaca09ccd8be49051b3ee155e2b3 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbb4ecd36df5aacab68f9d2702df56d4f963ce6394bdbbd7e6b33b0f2cbaf5e5 +size 29376512 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ce81d68706ae35171f1785a14cc777e33822b2d --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee0af80f04544f12f87ef90b58d11254f15f837467f5ceb0a15f4fa62395407 +size 100663296 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..14c16d320cb03ffea6a5675f543f7617e7e2c429 --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82ae2f0072d10866cb381d5a8b5ef1e60515f204164117ec34e741fc4581db1 +size 100663296 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..15de438dd5982b37b3025d7db4b0ead8247e66c1 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23424b63d230e2a0377dd18d56b845c1ecdf139fb3a0858432a531592ea0503c +size 25182208 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..b3bb76eba69ec6981cf0b109169dad8338d3e668 --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5ee866427a4963ad005de17627f957d77b00476bf7b22d41b3079697b162be +size 100663296 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..69fb4f0a6364a7024d9d861d5c36b5e69db77a40 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d00c90444abbb379c5124fe53ad0806feaa34d26e68aefd6c3de350e833ce23 +size 41943040 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ae2fa5ed4078333db0aa113e694e66cb513949e --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:001042b96e7e79795b9e7c8bcc3ee7d7d9d36e67f158240af1bc251a98a5c704 +size 33554432 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..86bbf8fb48773258057b756bd7681dc955ed6c17 --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796ded74a7a0b8ef3e2d8440587fe9fc5cf2639723b625cd05c7d990e9a4d612 +size 30408704 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..1bc7a8fa7576fa2476934563c6626e69995f38ba --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f36cd6eccbaa181ea4ee8ad957ee5919d99635535d20490f92dab7ca06da52 +size 100663296 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..31b70d37902774066d0f59975e66d9299187c6d3 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fae1e2f39fbfcded464397dce7e7c6c34b78b8dcb72bfd0e8e65833cc187031 +size 33554432 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..787f64a5d202cd13bf7954b38910668a282d5fd7 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:452fb5816a28271d6abc1672f97f733b2224bd3675524a9776ffa677a8021132 +size 100663296 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..1375694fc6593a8c0a1f684bd312193f5ea4649b --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99a43ddf3418038fc0789e0561831ddbdd48a5ff0f1c3d2057adbe5e3134eb77 +size 100663296 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..369ca1c8103bba0ae611945f549fe0c4a529e262 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b9035a0528fbe8770a7fbc4f8cb2c1e212265a9d7cd12b046b6981c8fe03d3 +size 29376512 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..40abcfc066061d8b64970b48b019cea88c62b92a --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09747d75cd9edee70fd0fa97673e336aaa0a6f863aaef20202f35fc809ce1f2 +size 41943040 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9ed23dcd7b0eb8e69fc3d9aff93e5f0c8d712cd --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b6ac77394f6d79ae4a660d608d450f24b0c66c3262b1c9e7d8d7dcb601b8d87 +size 33554432 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab2feb7560b4fc0aced88ab78b8569d00db9bb60 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9f7899749891643b6963caab28ac158f12c3d24ff6019c85ec8aed17b35806 +size 100663296 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8b16c66ea78dea27622f191c85c3f9d2829e941 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:522828acce7118be53b1584b63bc7aa23f33010ff4ffe25eea3f2ca4b5a931b4 +size 22020096 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..89e63dc6fac76685377c1366d5215e0ab63acf52 --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760e14ec70a14b617156b65bc1c0f1dd6bd2682f9d3eeaf4aa00b1937d3784e7 +size 41943040 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..77501b0ae0748b82a05bf601a85ba8617e4c82e3 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4acebb044942315904f10d1f549dc04ba74a9832c8764751a56c4bb0432373e8 +size 33554432 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..823c683b93337117811a36e44d08a5a28b9a9283 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5041c2cd4374cdbaa2ef99dcf841fef155ba0b59c7d46be46c50586a72261c +size 41943040 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..53e8158fcff0b8689210eddefdd457a407a6de42 --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ca8dc3b0717aaf99ca1642f989c53db63d02b46e7e6466c47e1fdcdf84ebce +size 100663296 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..7b847960643ca5da178e6e69f6c94aa30c4791a8 --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c22e263146e0ddd962b33457ce12dee2f7ad09f78f58dcd37546bfb1bb782f +size 33554432 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..ceb19e0312a39bc2694ccc1192c42ca3c88d481f --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb32f9d70834ffe13ca9248ec164f125e994b1ba27f82a9e62cc89f061a80e5 +size 100663296 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..d03fb0ccac7c513f78b1714ada5c2d3c8c682ab8 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5e40339bc5bb93be611615807a9ace7278612192721394527eb771b0437f54 +size 31473664 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..547cfbeeb37f0ab575fa1c173cdf03cceba194ff --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c7e42fa4d91ca033603a9a5f0eca427a4227ec1111f413a6c6b183fc1a578f0 +size 100663296 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f18a0cef081377f4d0e701be0c885e1f282eb1c --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25db8404780879b7153a56fdb1be3836cfbe5ac547f659d16ad420b8ca11cab1 +size 100663296 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..93c270c66820ec602356fbec256f4fd523b67d9e --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a694959b8898ddf0d61042da7754a1ffe0f00fe1b6d1743048883930308fe1a +size 25165824 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..c7b2c0a6d1a6975d22f9564811c3417076854ea0 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:687d1270236870f660216a8ecd9ebc6c0c72620af4ea176403f0aad261b90fd5 +size 41943040 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ba17bcc3143e966cbea2060c6c19ada6b1be84f --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:218f81a824154d4a157c480da028bb54ea2f2e6c637d31f884e834978756724a +size 33554432 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..bebd40360213b94d2396be2706a7bd70894a39ba --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f77055bc008b207567936bc860a68f99bd4eacc2866045204b73fef35a39e6 +size 100663296 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..1202ae7b2f6eff35223309e15e7ff08f5d51a729 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a4f891f80a862da9a3e8fe8d5607efa78ff7f43fa9c872616849858145af6b +size 22036480 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..4144fed6b8b6ed5d3c202cbb187261ef4f4e1384 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d074c08f05e31d7499838f35c77578b0eda7486ec30e3141abe574cba4cd1b +size 22036480 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..72c5c0b762da829bcf5b422e10157325963d9b38 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036a7b542dbcf333d56125e3675521978430b047a37eb5eb5ae8d18cc95b466a +size 100663296 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..53403ebffa3e255ba0385283018fc344846a03ef --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e1c7acebed4ebe4ed528cb6f06671a62a98f7cb510f78eab16a3b17bca6e65 +size 100663296 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..a54dbbdd183f127383e54d4fc2e4639e51f4271e --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da2a79e7c7cf9989734f8f3598bc7fe269cf84d9dd455f3fcb861f7203dd439 +size 25165824 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..e179fc6f942a8d6727ce0dad412c9c9f2195a775 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c001bc2a1088b18667b44dc990140f2aa704ebe0b3d53eddf608dc48b2c391d5 +size 41943040 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..4ac3307dd5124054858eb2eb770661c008be880b --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48eae406c7b1c590e5c22310f7b8920f26972615997dfa3f3bae0c88481ebd8f +size 33554432 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..61758c5cc661fc333a204e40c2ddc363abad1fd0 --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaea1fe60e3afbc3b214b2fae540ca0cef5e4a292b145c518cecf74bdc56abbf +size 100663296 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..1cb14f245384b35afea31f2d44e15b6787f4c5a0 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7d0b33dca4ec513a46fb159698ee60e1f3c607a497698206cc280a074ccb30 +size 22036480 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8bbcfc032c88594a258206ebd64a706083ea65b --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c1c8beebd73e4560610f464d32d097d7b6da1fc292fcbd64a84cb9ce233fb84 +size 100663296 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..894e8926e813fbd62f80b02cbbefb790ff5566ad --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62256e9cfa25cda46dc9cd8e28c51dfed24a6ff06b214615a2d5e653481ed024 +size 100663296 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..a78126c8c4af4b51955e3869030ffc31733fc2d9 --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96eaf18d4da37f881491e7df1d4a5e05660547c28fab0f702a8472749c64ded +size 25165824 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..cf1182973d73ba60dc35efde3593acfd870b7fc2 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1975b0a22c8a3cc7a218421740cbe76af8bb61d7f66df2f648e9fe7754c5a5 +size 100663296 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..62ae75449a6243d031cfa5466bd04524fef55279 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41fcb883ddacaa5a90b206e849ccaf759efe01d32fcb781e6509ec3312b14219 +size 41943040 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..01e9362518582cad9af0eab0a57b07c1be2709a4 --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6561911c0ae0f1ec28c42ac8ae82dd1499bca4952fa6c793ac39c7b8d8847936 +size 33554432 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..45eb89914b8e91cd80da3a199fa8a560c6045ca2 --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf963b3a266d136087d5d40232bc267a1fe1bcf3b896c65d1fa6b848a0736be +size 100663296 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..38b474b43b8a98917cc21fdfa007eeeaab65e5fe --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e67d744fae61e406ef5030c41e08c353166ca5dc38c56f2ec3475a2f44c236bc +size 22036480 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..fbb5a349355d4c68f6ffb6be280a461d11f013f1 --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d2f3e8b0a06a7a54398b8fa90b1d1f640833065588a9df4917caca28813899 +size 100663296 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..122ec37de2a177f6afaa2008a1ed23d643152f7f --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0156eee48b80ef509177bd0d4672c55553a860b33b62c7d448e1f8fd37daa1b1 +size 100663296 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..38946868cc31715e0a26d303befd04deab64f799 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c34caf218219c91378e7e92d5c11bf35f83e7903604a564097f23d8f07949be +size 25182208 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..1fbbb1c593ed3b80dcf24b995b727343574662f1 --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10efc8fcb4f57c9ee91b7df0fb81f4f7d8e82ba3a223cf5bc6f46e29f4a1b9 +size 100663296 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..94b216bfa946d26bb473faa18ade534f547c1bd7 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e294e292426bfbc1bad956a5c0c10d053a85eceb14d410599cee4ac1e7dc9d16 +size 100663296 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ecd678fd104814061f1962c7c9a40875e9fb088 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02ecffad674bd8637e16aaad29cac45b5d0e9fe09b8ff4cff1a744df9d1a60d2 +size 25165824 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..a91fdaf5d4a2a2f12c3b109f62b3d860deff5344 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1cca1e4d14511e9848f006c312fef11579c1401f7571e074a8d599d167db9d +size 100663296 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec40bf83be6d8d5e5717731e4f15131914259d35 --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7c6627c8c33c23a8be2c959b54d05805f37c2836f94927cabf56bc6e528bf6 +size 41943040 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a66ea982a39efca414e94e0e649a356ce5c1710 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b1755f1d16cf5f42aa2acb473a1717f6e83d2fabf063cf370bd283ede8205be +size 33554432 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..61c5bd1be486a52f979d807ed95c2c0629db0fab --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02a57666869eae122f0d14dc4daeeb6b79157c5fdaac30b5d0df4b0fca06c60 +size 100663296 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..74b908f5482234ad64b2ead6ec008eb09a6c25b7 --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870e0f44bc40d75f9aa2f99759e19ae54dcdc3f83bc7f71f2f4c05ffd89f8532 +size 22036480 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..6bc2dc567ea323c2902d5a40ef2609705b428607 --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566482fb3556cbd4778c1a6d5bb16416eeaed543ea9a0807a1bcbced22838e1f +size 100663296 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..904fc5df5683197d4c13eb37b9bf3709b1c943c7 --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f56f9eaec2ad055f5ef51d6c8e77f734cf66545c0e14ef692420f856aaab805 +size 100663296 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..6bb3748415d84540bfa97fcb4e5442ef51048db7 --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb92a48f36ca1a1d1df2738f0ab7a29932831d04a3962634b069ead3a9af0f94 +size 25165824 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..3253388d2fb46a99918e4f058f4532a4cd66d22c --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872ca4cc1d5fdd8cc97bcabef3653d161d79bf1ac93a7c1320d470ba72b9d785 +size 41943040 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..565747494f62cd766fb3a1d9d5c5b01da04a33c5 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aca51a4e45c913ed52869c3283baa14e2889e7d731e8688eeb6d9b46b6c007d +size 33554432 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..69ba931b955237b15682ae895eefa69a6301b4d1 --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57911f752c789dc7cde8047a2332dcc19356d482a6f893ab2717bf17a988de80 +size 100663296 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..77817dacb5ed491617972e623a8f087036363a81 --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d241d838935cca7a070e19835d8919a449e29641a3f9c8159e34c39290aa9d +size 25182208 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..f57c4b15b96607193bd10f7bdc84d26b324569fb --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80bb3955b758208cdd86632e97c3f282901a5a9f35ff55e1773a3521c96f9d67 +size 22020096 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..da5a786ff048cae71611959d20e1b7d15d93ebdb --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4acf51cf3a772baa1e6a1da5959621a3c3cf6ce89533db9c8665fc03c9440341 +size 100663296 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..f4c11a940e811a26d9168209daeabebd03545f18 --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28d8a851380039afb967b341d4be13b82ffd540ef8e295e8c6e017b01780ae9e +size 41943040 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..f51f230f3c2499c46970e75f43f665dff5ee6a9e --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a29d18fc33cbb41e82d971d032b5285dd8c5462a36e0a0e1d85b38cbb9caad5 +size 33554432 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..427e04ac3db516f574cd6fe7942d1e5544c9387b --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a30efcea2d53dfdfcf9357eda87ecfdc2f8c51fdb9373b61b94962f0a6bfc1f +size 30408704 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..d37f05930c7bcfb2d42490818a1ba4d3166a5c60 --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9d9ed2ad190f4b782d94bc6403f78d3b569db0adb5e803f863b236cea5b636d +size 100663296 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..aecbf61d78b1bbbc0223fe8adaed93ce89f36a97 --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:398571002d71814a51dd6128f24639ed70e541ac2132f2acc5e38d006dc8a606 +size 100663296 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..9930ef80b73e1109aeba0be335a94f114e8bcc9f --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7debecdf8de01435a455cec2a0d4230e969651f8fb8a219cff5bb4a4b3e5a7de +size 100663296 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b4d47f03f24483a00a090ab2de169bebec6d3c0 --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2daa9acefef5a491186ccec26fb8fb27f613981840071444ea417214609656cf +size 29392896 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..48ad6d142187bc2b23b34ee73f3ff8f2af13b5e1 --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e777a80d2825e848b6c5bed3941bdd32f477f5f55048f0819c1be252844deea6 +size 100663296 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..3fcbb1e649a5a5ea140fcdbc678be182692d5cd8 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e773a231706a3ee5d05050ff27aa122a19df09ee7dd59eafa906b7487035b9 +size 12778456 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3a34e67f5faf069bdfc8dd0e614441ea7b2a9a0f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,370 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": 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": true + }, + "5": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255000": { + "content": "<|START_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255001": { + "content": "<|END_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255002": { + "content": "<|YES_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255003": { + "content": "<|NO_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255004": { + "content": "<|GOOD_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255005": { + "content": "<|BAD_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255006": { + "content": "<|USER_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255007": { + "content": "<|CHATBOT_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255008": { + "content": "<|SYSTEM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255009": { + "content": "<|USER_0_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255010": { + "content": "<|USER_1_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255011": { + "content": "<|USER_2_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255012": { + "content": "<|USER_3_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255013": { + "content": "<|USER_4_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255014": { + "content": "<|USER_5_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255015": { + "content": "<|USER_6_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255016": { + "content": "<|USER_7_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255017": { + "content": "<|USER_8_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255018": { + "content": "<|USER_9_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255019": { + "content": "<|EXTRA_0_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255020": { + "content": "<|EXTRA_1_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255021": { + "content": "<|EXTRA_2_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255022": { + "content": "<|EXTRA_3_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255023": { + "content": "<|EXTRA_4_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255024": { + "content": "<|EXTRA_5_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255025": { + "content": "<|EXTRA_6_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255026": { + "content": "<|EXTRA_7_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255027": { + "content": "<|EXTRA_8_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255028": { + "content": "<|NEW_FILE|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255029": { + "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255030": { + "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255031": { + "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255032": { + "content": "<|END_OF_MIDDLE_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255033": { + "content": "<|EXTRA_9_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "chat_template": [ + { + "name": "default", + "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are a large language model called Command R built by the company Cohere. You act as a brilliant, sophisticated, AI-assistant chatbot trained to assist human users by providing thorough responses.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}" + }, + { + "name": "tool_use", + "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{'\n\n## Available Tools\nHere is a list of tools that you have available to you:\n\n'}}{% for tool in tools %}{% if loop.index0 != 0 %}{{ '\n\n'}}{% endif %}{{'```python\ndef ' + tool.name + '('}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ ', '}}{% endif %}{{param_name}}: {% if not param_fields.required %}{{'Optional[' + param_fields.type + '] = None'}}{% else %}{{ param_fields.type }}{% endif %}{% endfor %}{{ ') -> List[Dict]:\n \"\"\"'}}{{ tool.description }}{% if tool.parameter_definitions|length != 0 %}{{ '\n\n Args:\n '}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ '\n ' }}{% endif %}{{ param_name + ' ('}}{% if not param_fields.required %}{{'Optional[' + param_fields.type + ']'}}{% else %}{{ param_fields.type }}{% endif %}{{ '): ' + param_fields.description }}{% endfor %}{% endif %}{{ '\n \"\"\"\n pass\n```' }}{% endfor %}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \\'Action:\\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:\n```json\n[\n {\n \"tool_name\": title of the tool in the specification,\n \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n }\n]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}" + }, + { + "name": "rag", + "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{value}}\n{% endfor %}{% endfor %}{{ ''}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Carefully perform the following instructions, in order, starting each with a new line.\n' }}{{ 'Firstly, Decide which of the retrieved documents are relevant to the user\\'s last input by writing \\'Relevant Documents:\\' followed by comma-separated list of document numbers. If none are relevant, you should instead write \\'None\\'.\n' }}{{ 'Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user\\'s last input by writing \\'Cited Documents:\\' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write \\'None\\'.\n' }}{% if citation_mode=='accurate' %}{{ 'Thirdly, Write \\'Answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.\n' }}{% endif %}{{ 'Finally, Write \\'Grounded answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the symbols and to indicate when a fact comes from a document in the search result, e.g my fact for a fact from document 0.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}" + } + ], + "clean_up_tokenization_spaces": false, + "eos_token": "<|END_OF_TURN_TOKEN|>", + "legacy": true, + "merges_file": null, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "CohereTokenizer", + "unk_token": null, + "use_default_system_prompt": false, + "vocab_file": null +}