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/README.md b/README.md index 7be5fc7f47d5db027d120b8024982df93db95b74..503c97c1731ce183c91a8b1ef072af141123eb78 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,11 @@ --- +language: +- en license: mit +base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B +base_model_relation: quantized +library_name: mlc-llm +pipeline_tag: text-generation --- + +3-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [DeepSeek-R1-Distill-Llama-70B](https://huggingface.co./deepseek-ai/DeepSeek-R1-Distill-Llama-70B) for inference with the [Private LLM](http://privatellm.app) app. diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..2f98e357c05745bf2cf79816dbac3b1d79de5789 --- /dev/null +++ b/config.json @@ -0,0 +1,5 @@ +{ + "quantization_config": { + "bits": 3 + } +} diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..67c4957c9bd889908954bb95f8c2499cc42db133 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,12343 @@ +{ + "metadata": { + "ParamSize": 805, + "ParamBytes": 31776318464.0, + "BitsPerParam": 3.04023285660184 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 420679680, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 128256, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 420679680, + "byteOffset": 0 + } + ], + "md5sum": "9cf16ebcdd3d9a19e4049558f6b42e90" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 52584960, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 128256, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52584960, + "byteOffset": 0 + } + ], + "md5sum": "1f30e44d9b43b26ca88956cdbfa05437" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.78.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "d54a62e9cab21ddc05182e07e2786e0c" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.79.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "395d9caf2bb0d5973a584b903ba5d04b" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 23560192, + "records": [ + { + "name": "model.layers.78.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 0 + }, + { + "name": "model.layers.78.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 16384 + }, + { + "name": "model.layers.78.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.79.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23543808 + } + ], + "md5sum": "ff3f529a8bbe11c1aa3b393e8da29e5b" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "8c6f4d67864bbc1bf600ad1ae5b3ea5c" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "b0d600a479894cd42b0529bab0a03df4" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.79.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "2bf10be88ca61c2e78d91de4e562f3a8" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.79.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "a00f7a03d1ba55099dec2fec43c01bd4" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 420679680, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 128256, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 420679680, + "byteOffset": 0 + } + ], + "md5sum": "4b63bbd661056dbef8cb4b022f7e9d80" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 52584960, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 128256, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52584960, + "byteOffset": 0 + } + ], + "md5sum": "0e3738fae1222d3b78775b5b399caacb" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "88c54d298d2ab932d67bf57f919a3602" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "0c34ee932cba906439f0e3e7bc3effa1" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "3bbe69ffb6c64012c12958f73820d779" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "23ad995e3f0a1770bc31077cd46b98be" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.79.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.79.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.79.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.79.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.norm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19337216 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19353600 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "6c5bbc14ad0a46e2c8316b2801eb7294" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "12fcd2a3eaf02baeedb07b5a4ab25769" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "5501dff64322180d467c20037d4244ab" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "58381ad0023f210935b3ad4c6f8e7b35" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "70be19ba6f0f3144bc37fb51c4522c45" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 3358720 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 26869760 + } + ], + "md5sum": "0e923cecc32bbe5fabc4c66a67fce5f7" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "ae80ac9eabded000ad9922724cb41609" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "7fce7b2aaceb9a540a8ee1430c7f3ba4" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "5d53eed196aefc4a231f346d6afe91d1" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "477957bfe3dd4afd6924392cd7c854ea" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "29feb063350a34afc5b720d18d52b075" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "b639a134d1115f8148541b69e14cd31b" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3375104 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15122432 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15138816 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 15155200 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26902528 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 26918912 + } + ], + "md5sum": "68b8fcd6db03718cfb3ecfcf44e15acc" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "9985781aefb1b8ee2b1f2b29f480ba7c" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "772c83776dfa54b6a6f9a97e529855da" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "dbbd1d69758002fdd901af1492e61629" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "8468f881a962408d94d81072e3f8d6bb" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "53699a08416db230ecd09ccef3c70c7f" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "059c6fada6395aae162732425028a916" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "9f28a036bdb2e7f83e77a00234a262d9" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "c784d8261494e758b0aa4a68ac75e04f" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 30269440, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3375104 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15122432 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15138816 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19337216 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 22695936 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 26894336 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 30253056 + } + ], + "md5sum": "ba37f314d2a9b3c64ea47c45cc3eb57a" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "183fc514ef46a424ebdc4f97c937dd22" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "543117a8b009e43e7afbf61cbb562088" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "49148dde9a81999a8a5bc9191cd588e6" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "045e6458263f9ce6aaf9de24f19f64ac" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "13775d67866ef1560e4f3b0c3e84ccaa" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "3251104b193fc2d0c1cf3f3011750778" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "9fe884085d95990d2f08599ccc262167" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "896dadf2be68ad3ea128d8debfc2e2d2" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19337216 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31084544 + } + ], + "md5sum": "1c2213dc32b6d730adfe6aeebf97d8ee" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "1d254be490572d32d65c4eb095907d65" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "e91a637a6cbc4ec1978dafc682b34abc" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "1f60fa6cafab00ea46cbfc94e404acf0" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "0ce7e7036346af5c4b25a90f75f35cd0" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "1fe62af5fd77464964d93ae6ba9fd015" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "727e0e7fe901f1eefc95e16441013310" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "f0383ee3721ece83dafc8f67688d1cc1" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 22712320, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 3358720 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 7557120 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 10915840 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 10932224 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22679552 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22695936 + } + ], + "md5sum": "e7b8e54e7d296b1616d4a9ab5e267b75" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "1c816c55ce0f7f7170efbb9092dc517b" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "8a1de9f54703400c28ed6e69b3bcae35" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "bb294ace18d145cba2a689ce85fe7a48" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "c9b9db73ff52cc2d06528e3ec63a075d" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "cbb09ff4f570994bf60936c2420c5d65" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "8a3fef073262d304a4b35907831cd66c" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "debee6ce0d7982509cd098afea72c1d2" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "cc2f85d151caf5ffd2249fe50b9dabbf" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + } + ], + "md5sum": "47c130d9b9de9bd0ddbf0e1ac0527f2e" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "c6264ad1d1778ff339445fe80f6232e6" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "8aa64480107d8b55289271dd2835142d" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "923f8dd1bb1b7147939fc04b39177773" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "9f706135b56bba2cc21bf92d96b33aba" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "45039ea9e63d7da8ed23510901c75827" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "9f651e1247a05fc2983cb02b8f4971f5" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "cbdc2f4b40236ae5a5ed5f4795720d9a" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "c344a5a8b76c78c9f8e3ddb30a0613b5" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11747328 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15945728 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19304448 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19337216 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19353600 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "94dcf6f75da190e69eeeedcf0289156c" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "555d41b504029b27e2834b15e79088c4" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "c866f8a984541f7416860f7b0380f8c1" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "5c5db0269f29aa6711e9801ccec7281a" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "e37a02e7aef781f97b2f2d132d5de283" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "6d35ada7607b32b4818911af33e72982" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "800c53aa0f1c7122a4dedda2ba8fd0a5" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "5998c7c4fcb64d871741af803fc84d70" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "3456ce8e95b11f96965c926d18e571fb" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "96ea19171675fdd4621a5b2d0a1ce2c8" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "17fcbd4d3613eca13e14d347e7a3e3b8" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "bfc1cddce73c4da14fdea3f6b9f47fc1" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 30269440, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3375104 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15122432 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15138816 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19337216 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 22695936 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 26894336 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 30253056 + } + ], + "md5sum": "a5ed985bfbfd9276287d62b917af7d99" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "d23f4bc842444f51143ade0956062c32" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "1c7130be3bdac725a99684c78987716f" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "6b2c4a20b6369acfe9f93473cd1abc55" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "6b8b31e03a63c2952b8ee702c49484e3" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "24dbdf3b012dd846ea93169ad2309ba0" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "372a701d51b251cdfd34d57d91a44598" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "bebb13fe61b73983b01928dee833a3a3" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "faabb29ab41e37ae892c57693632c055" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "63d55cd542d066b504af5a5439d35532" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "9f3813ebf596a1431229ba7b759c7e73" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "13443ab1c60a25292d2f945a374e5bc7" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "3a5ad84d03791214dc27520486e216d2" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "24168a34a4f25db538f95c004aefa640" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "7a3ca1df263346cce19114e48ee62a60" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 26894336, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + } + ], + "md5sum": "d01d650dfa6c19face9030dc9ba25aee" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "6298766803575885cf3f7cbe2b265480" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "a7356ab9d90d1055e4cfce9d7ea97cae" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "50177fac4ee4c596520205a822414aea" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "d0d9f11cb77c8ff85828f3d5bd782a22" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "eabf1f8f37568a9ecf29e11f898b5a9d" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "9ea690931ce61eabd27dc1743fb00444" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "9eb1d28ff8fb0c9220e6b5665d96844e" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "31282f37d6e6c983463d4d7e57a328ba" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + } + ], + "md5sum": "2fe2cd9472e9514917e87f458c74fbbb" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "70ebb4d14e7f6d9061ae2d4f0bd2ebfb" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "bf8e87906cbf4ba6fe2b7a0bc3787ec6" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "3af01fdb156f8fb313a1617deabf96d2" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "916e1c720bd2dc611a6f6b39e1ae253a" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "075cef8c3f1289447d7b54e11f0a0494" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "c3705adbbebdd76054698a53fa9449ca" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "0d7dbca1751b6b3b391c6b9cd84dc0c2" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "9ecf8eefbcde5c17584baf8821eab1cc" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11747328 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15945728 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19304448 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19337216 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19353600 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "ad85e8ca3d41c7197e20b310596936d6" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "941eb3118de69347cf3e43304492a044" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "10ed72e3f63ca406eb76d0135e4b6198" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "1091738f536716d57012194dac1a4dfa" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "7ff9e5181b5c90e15bf579a110d93936" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "8b4aa9a8dfaced8d8384fd0b3cc47df6" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "b412e678a0618fb9562e1b4ddab412d2" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "d76c7ccc88313c94fe79340b6fc1d7fb" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "7fee9f06ee9c4fc4915c18531f1a1847" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "406b60542a12d170f37edcbd81052b76" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "a0d254f320dae62360f566c559c0e4cc" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "a1569b70b850e8a33b5663486072d73a" + }, + { + "dataPath": "params_shard_128.bin", + "format": "raw-shard", + "nbytes": 30269440, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3375104 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15122432 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15138816 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19337216 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 22695936 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 26894336 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 30253056 + } + ], + "md5sum": "ff8bae7b5593874f0d2dddfda58a412c" + }, + { + "dataPath": "params_shard_129.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "fe704b9f6ae36ff4e950c05e00ad194a" + }, + { + "dataPath": "params_shard_130.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "7098b10b3cf82f7f975ce9815b2995bd" + }, + { + "dataPath": "params_shard_131.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "dc1940a5692fda5bd7018d876cf0a136" + }, + { + "dataPath": "params_shard_132.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "14c446581193398e230816e28a5053d5" + }, + { + "dataPath": "params_shard_133.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "c5a4d607feb1435ad6a62ae2aaf93bf3" + }, + { + "dataPath": "params_shard_134.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "895f3611c7380de80e45b7f132fa478e" + }, + { + "dataPath": "params_shard_135.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "a89dd883934908af97e08e1a2710bc12" + }, + { + "dataPath": "params_shard_136.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "16fa5a99732eb464535e1fff9b972855" + }, + { + "dataPath": "params_shard_137.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "23060fa859787dafd297245b0a88d338" + }, + { + "dataPath": "params_shard_138.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "3e877876e2882409854da94131f5124f" + }, + { + "dataPath": "params_shard_139.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "2a49e8a6a56ff30d48f9c0497810f52d" + }, + { + "dataPath": "params_shard_140.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "116d8d0a8ee87078e64d5269c8e8b5cc" + }, + { + "dataPath": "params_shard_141.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "90aa5d29eab0792047b56bc7210fd61f" + }, + { + "dataPath": "params_shard_142.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "300bdc1aa30f4bd59acf32a97b09742d" + }, + { + "dataPath": "params_shard_143.bin", + "format": "raw-shard", + "nbytes": 26894336, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + } + ], + "md5sum": "d823142a135bb2055fe3de15cce00189" + }, + { + "dataPath": "params_shard_144.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "39aebba9a7c7197ac712f5da4ce3ed95" + }, + { + "dataPath": "params_shard_145.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "f6b12e1c8eb73d30a2a4e04c778e952f" + }, + { + "dataPath": "params_shard_146.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "cfff1a63ac021b90bbd3ef33282953c0" + }, + { + "dataPath": "params_shard_147.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "74df906c809a660043839ac71af4bfe3" + }, + { + "dataPath": "params_shard_148.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "ad70c4c88591d0e722c37ee14a5082af" + }, + { + "dataPath": "params_shard_149.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "f19614c1ae428e657973cf31374c8188" + }, + { + "dataPath": "params_shard_150.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "10d5b100d518658cee8d7f0ef76b3312" + }, + { + "dataPath": "params_shard_151.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "624594c2e8b2d9d02f32a759dd2304a9" + }, + { + "dataPath": "params_shard_152.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + } + ], + "md5sum": "63b5655d8c9e2a7fde38d38072c473f2" + }, + { + "dataPath": "params_shard_153.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "0738c7a3026fb6e637c104c0f4e74d05" + }, + { + "dataPath": "params_shard_154.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "e8d5bb1c9b3b75dfcece99d0c70d5af3" + }, + { + "dataPath": "params_shard_155.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "ed241f7c2fd980f05c57fef496bc53b6" + }, + { + "dataPath": "params_shard_156.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "0dbd74c13f476b0fa02e2cdca4a35cf5" + }, + { + "dataPath": "params_shard_157.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "71c52adf6c6131625b4c14b3bf285575" + }, + { + "dataPath": "params_shard_158.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "a0b4693a36f2bb8e5acc4c65df9b8a95" + }, + { + "dataPath": "params_shard_159.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "288a9f66ed8d2a96887cafae76f92e81" + }, + { + "dataPath": "params_shard_160.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "c550e69b0f855d36beb2aac2a362f443" + }, + { + "dataPath": "params_shard_161.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11747328 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15945728 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19304448 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19337216 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19353600 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "374953ab0c77a73820a7b49ad6140d71" + }, + { + "dataPath": "params_shard_162.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "40c815a6d724a87e527f56be533ac64a" + }, + { + "dataPath": "params_shard_163.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "984268a61f739fce0192a306c556d172" + }, + { + "dataPath": "params_shard_164.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "6fa12cfd0ee7576ae379b73579ce1363" + }, + { + "dataPath": "params_shard_165.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "4e295fe9535142fbd4bc146f5f82b48e" + }, + { + "dataPath": "params_shard_166.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "72d40a774a8b55cdd2916b6fb2e1994b" + }, + { + "dataPath": "params_shard_167.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "03449d6ed9410bb1dd7c30bc75d9fa52" + }, + { + "dataPath": "params_shard_168.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "f9d0570096e1c0698964db1c45b55b72" + }, + { + "dataPath": "params_shard_169.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "2fdd3ba9a5c8f70d62f13186d7c8803f" + }, + { + "dataPath": "params_shard_170.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "ce6afe286907a53fc420e7ca64b41826" + }, + { + "dataPath": "params_shard_171.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "23ec26dcd64ab0ccbbda2858176c9662" + }, + { + "dataPath": "params_shard_172.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "911af899002876cb89aa50e220c317fc" + }, + { + "dataPath": "params_shard_173.bin", + "format": "raw-shard", + "nbytes": 30269440, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3375104 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15122432 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15138816 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19337216 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 22695936 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 26894336 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 30253056 + } + ], + "md5sum": "7955cd79ab3e8362ec15fa68b39f1806" + }, + { + "dataPath": "params_shard_174.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "0c07c7c05cec72cdee3b2c6420f682b0" + }, + { + "dataPath": "params_shard_175.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "90de00ae7c36e5635df8ec32c8f16df4" + }, + { + "dataPath": "params_shard_176.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "9ddd74734cd813b713d978612cc69177" + }, + { + "dataPath": "params_shard_177.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "526abb9885689ef2434fce560ddad9cd" + }, + { + "dataPath": "params_shard_178.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "7530fa7d6e17a399ce6e4a834f1e53d3" + }, + { + "dataPath": "params_shard_179.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "a93757d88344de77e01cd9e5703e3dda" + }, + { + "dataPath": "params_shard_180.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "de4038f7287cfe1e47fbdef181eb1bbe" + }, + { + "dataPath": "params_shard_181.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "8fa10cc1b293da3d7783f47dddf4cfdf" + }, + { + "dataPath": "params_shard_182.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "f5319097e95f8c96a6199cdb56d66767" + }, + { + "dataPath": "params_shard_183.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "63003b043faf3fbc35e4b50b35fd7027" + }, + { + "dataPath": "params_shard_184.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "4f9d711992a5a692d1e66112321cb1ed" + }, + { + "dataPath": "params_shard_185.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "9def2286b82c6f67105026a64068448c" + }, + { + "dataPath": "params_shard_186.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "4cb72c18fdf6f2b3630f0e5ba34e42d8" + }, + { + "dataPath": "params_shard_187.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "c8c4c601127800c63317a74c6dbffba2" + }, + { + "dataPath": "params_shard_188.bin", + "format": "raw-shard", + "nbytes": 26894336, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + } + ], + "md5sum": "374746bc5105231c7f3fa93f44ff6ba7" + }, + { + "dataPath": "params_shard_189.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "fca8829c2fb9463b1b0cd0db052fd1a4" + }, + { + "dataPath": "params_shard_190.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "f409ef7778e0286082cf2a8f592b17c6" + }, + { + "dataPath": "params_shard_191.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "654f623db5824706c7b565bf8afd3755" + }, + { + "dataPath": "params_shard_192.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "035ed28593d294fa252813e102c89f8d" + }, + { + "dataPath": "params_shard_193.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "a0b3ef979af1e3a4c44ab0cfc430195c" + }, + { + "dataPath": "params_shard_194.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "efc3ffc6588aeb5fe3da9c6991302701" + }, + { + "dataPath": "params_shard_195.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "3a966285289ef0388b8d6ed87a1553b9" + }, + { + "dataPath": "params_shard_196.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "86e0822b21a813bfc41b21d220f3a7d0" + }, + { + "dataPath": "params_shard_197.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + } + ], + "md5sum": "608f07f6fbb28b5d8eca199995bf9b42" + }, + { + "dataPath": "params_shard_198.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "14cbd389c7db4ef928e28384808f08cf" + }, + { + "dataPath": "params_shard_199.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "3e8dbfa99ff397ba9ea0e2ea39488f02" + }, + { + "dataPath": "params_shard_200.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "943894e63724178fe26a57a7f2ce8ea0" + }, + { + "dataPath": "params_shard_201.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "052cac5831a5db7ee26fb2258ffc8bd9" + }, + { + "dataPath": "params_shard_202.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "d98291ad658db9b5acf81b129267dec9" + }, + { + "dataPath": "params_shard_203.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "0db37e5c06a3bd536c237a8eec7901d4" + }, + { + "dataPath": "params_shard_204.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "7b9ea9d35c8841764d4fda856fd4f487" + }, + { + "dataPath": "params_shard_205.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "80dd69da7e04a9cc9fd5f6228df74a24" + }, + { + "dataPath": "params_shard_206.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11747328 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15945728 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19304448 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19337216 + }, + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19353600 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "f0f3b7e8fff0c47343dc210ad2694d27" + }, + { + "dataPath": "params_shard_207.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "f37b25ab40cc7c27610d3fda2518d1d7" + }, + { + "dataPath": "params_shard_208.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "c9bb013f7a25876b8ddf2cb285c4b7c1" + }, + { + "dataPath": "params_shard_209.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "fbbbe64abb9ac903c545f268902240df" + }, + { + "dataPath": "params_shard_210.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "c5ddbe456cfb8e3cf7bf93a2fd5ce714" + }, + { + "dataPath": "params_shard_211.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.40.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "77b1b1ce014ec1887756d33488d90c58" + }, + { + "dataPath": "params_shard_212.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "e2c948d06f98a75ba91dc8b163915dae" + }, + { + "dataPath": "params_shard_213.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "6261aed539e3a59da6c7a3d4903ea032" + }, + { + "dataPath": "params_shard_214.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "a0fe6a3f6be8074ef74560eaff92da2b" + }, + { + "dataPath": "params_shard_215.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.41.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "a6db1247982c9621ec7d79c079a8ad1f" + }, + { + "dataPath": "params_shard_216.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "73b1a4862a7352ddaeceb8a2aef0919d" + }, + { + "dataPath": "params_shard_217.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "b4e27f702c36255068544fd85ee770d5" + }, + { + "dataPath": "params_shard_218.bin", + "format": "raw-shard", + "nbytes": 30269440, + "records": [ + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3375104 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15122432 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15138816 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19337216 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 22695936 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 26894336 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 30253056 + } + ], + "md5sum": "6677ba3c99d54a76e25ab78854cdf22f" + }, + { + "dataPath": "params_shard_219.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "94112b9d141fd921c4f58df9405f04f7" + }, + { + "dataPath": "params_shard_220.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "2a09746f9c99503084bbd1e6b125d1ed" + }, + { + "dataPath": "params_shard_221.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "140af1644075f3c9f2bebd6709b819cc" + }, + { + "dataPath": "params_shard_222.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "daac6fe6cdb4f7f5ae38bc81493ceaff" + }, + { + "dataPath": "params_shard_223.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "eaed9053f2f933cf5b4fb92d1268825f" + }, + { + "dataPath": "params_shard_224.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "aa1c3d7a0dad8ba776f2f1ce73372dae" + }, + { + "dataPath": "params_shard_225.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "b7a657cccce0b58c27068d77bf9372a6" + }, + { + "dataPath": "params_shard_226.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "70dc849d5aaafcf82a5f223fc41a44bf" + }, + { + "dataPath": "params_shard_227.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + } + ], + "md5sum": "6ed0cafe50f6b67e081fc3f6ee01a244" + }, + { + "dataPath": "params_shard_228.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "9e476b43ce330359db33d546506844ee" + }, + { + "dataPath": "params_shard_229.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "08e1f6d95457cd376db8529ad87bdf69" + }, + { + "dataPath": "params_shard_230.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "6a60c2ed09a74fc4ea1d87735e487ec9" + }, + { + "dataPath": "params_shard_231.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "608511594e311e411905cc2e93c7aa6a" + }, + { + "dataPath": "params_shard_232.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "46de445936c4820a1e304443e238b7e0" + }, + { + "dataPath": "params_shard_233.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.42.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "a4236d62f7a7af76b6432650fb3216ad" + }, + { + "dataPath": "params_shard_234.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11747328 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15945728 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19304448 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19320832 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31068160 + }, + { + "name": "model.layers.42.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31084544 + } + ], + "md5sum": "4c82bc583262266778099ce86cf904d3" + }, + { + "dataPath": "params_shard_235.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "70fd1a4aec6c2534dc2502acf32e8c6a" + }, + { + "dataPath": "params_shard_236.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "9bca567ef3736eab30d5ae64cae33a94" + }, + { + "dataPath": "params_shard_237.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.42.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "6d32b787010ced0fd24aba21b30f7fce" + }, + { + "dataPath": "params_shard_238.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.42.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "d4a7f5f7380baf93210bad3825c9091d" + }, + { + "dataPath": "params_shard_239.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.43.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "dbef8d16523ad01d4dea73bc99bf1795" + }, + { + "dataPath": "params_shard_240.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "dfea6996890f96432e3356e7e2a70d1f" + }, + { + "dataPath": "params_shard_241.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "5c0ba0a26c750b81406fec07ca3fe583" + }, + { + "dataPath": "params_shard_242.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.43.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "e0df1c2a618f75db87e8201d548a874d" + }, + { + "dataPath": "params_shard_243.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.42.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.42.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.42.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.42.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.43.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.43.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19337216 + }, + { + "name": "model.layers.43.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31084544 + } + ], + "md5sum": "b7a4da264d3ab1c0ef83fc04f7da6c4f" + }, + { + "dataPath": "params_shard_244.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.43.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.43.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "914395e29b6c173d0ef3c15f1a983761" + }, + { + "dataPath": "params_shard_245.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.44.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "d253eff959a4318fce6ce2e2db19c44f" + }, + { + "dataPath": "params_shard_246.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.44.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "aea3810f2080f162da2f3fce05164829" + }, + { + "dataPath": "params_shard_247.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.44.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "9dd6b0dc7fbaa4bd2d31000e6e747e47" + }, + { + "dataPath": "params_shard_248.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "6d9cd8485e5ad942d46cc1fd5288ba5f" + }, + { + "dataPath": "params_shard_249.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "f53b83a7bf349f846eb9d04134b795ae" + }, + { + "dataPath": "params_shard_250.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "9945a30f42dab71760552def5d4f8424" + }, + { + "dataPath": "params_shard_251.bin", + "format": "raw-shard", + "nbytes": 22712320, + "records": [ + { + "name": "model.layers.43.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.44.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 3358720 + }, + { + "name": "model.layers.44.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 7557120 + }, + { + "name": "model.layers.44.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 10915840 + }, + { + "name": "model.layers.44.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 10932224 + }, + { + "name": "model.layers.44.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22679552 + }, + { + "name": "model.layers.45.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22695936 + } + ], + "md5sum": "f6dbd5c0aed9c7569e1a965d43194985" + }, + { + "dataPath": "params_shard_252.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "2df6d8933ebb4771f2240150bb9371a3" + }, + { + "dataPath": "params_shard_253.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "c68220e28908e7c92614e216754aa2ef" + }, + { + "dataPath": "params_shard_254.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.45.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "afe273289b43b5d74653f7f635d275a5" + }, + { + "dataPath": "params_shard_255.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.45.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "83811da946a61727bb1a30199778bfb7" + }, + { + "dataPath": "params_shard_256.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.46.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "4fdf33ab6eb078764439c9c55e54be5a" + }, + { + "dataPath": "params_shard_257.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "28b2913582e6cc5dd6a3223d3d2bc2c6" + }, + { + "dataPath": "params_shard_258.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "9c34d6fb14b1a0874e46d19a34872021" + }, + { + "dataPath": "params_shard_259.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.46.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "b0f05af4d20efb91e3aaa404cbbdc5d1" + }, + { + "dataPath": "params_shard_260.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.45.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.45.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.45.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.46.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19320832 + } + ], + "md5sum": "467439c64ea50e0aed257940fcedf180" + }, + { + "dataPath": "params_shard_261.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.46.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.46.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "19e3dc9d692e0cb81433f7a8ea77ba3e" + }, + { + "dataPath": "params_shard_262.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.47.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "5bec5725e844924251cae58a0bae8d07" + }, + { + "dataPath": "params_shard_263.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "a301f551b9a17f83f074e911881591ef" + }, + { + "dataPath": "params_shard_264.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "884aba1d6c09f549763b672c1d68225e" + }, + { + "dataPath": "params_shard_265.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.47.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "d3c2ba0605309e325da56883d8ffcff8" + }, + { + "dataPath": "params_shard_266.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.47.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "a338b3ad38e1c20858e66019363a2d57" + }, + { + "dataPath": "params_shard_267.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.48.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "192fc757a9b406854f3f306ff1ab0dca" + }, + { + "dataPath": "params_shard_268.bin", + "format": "raw-shard", + "nbytes": 22745088, + "records": [ + { + "name": "model.layers.46.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.46.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.46.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3375104 + }, + { + "name": "model.layers.47.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3391488 + }, + { + "name": "model.layers.47.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3407872 + }, + { + "name": "model.layers.47.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15155200 + }, + { + "name": "model.layers.47.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15171584 + }, + { + "name": "model.layers.47.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19369984 + }, + { + "name": "model.layers.48.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22728704 + } + ], + "md5sum": "799dd5d04234507801f4fd3fbb58b457" + }, + { + "dataPath": "params_shard_269.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "0afbf5964578bb7fbf2183438593609d" + }, + { + "dataPath": "params_shard_270.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "cc04405748b7b2de2785e956165fdf1f" + }, + { + "dataPath": "params_shard_271.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.48.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "b01c362f7f6d570a3dd647c8bbb89a31" + }, + { + "dataPath": "params_shard_272.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.48.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "d02d185b741a7960fced892533c9f7c7" + }, + { + "dataPath": "params_shard_273.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "43298336f055bd26ab1602dbe4692a26" + }, + { + "dataPath": "params_shard_274.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "0ba6b3b4c3fbd0491682c24a48bbd1a9" + }, + { + "dataPath": "params_shard_275.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.49.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "22fde47255c3f5977e06147d0ab35660" + }, + { + "dataPath": "params_shard_276.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.49.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "5d84379eb88fbdfd5dfc4117b7605c47" + }, + { + "dataPath": "params_shard_277.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.49.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "b8a7b9f8119d4badb593db6be906f431" + }, + { + "dataPath": "params_shard_278.bin", + "format": "raw-shard", + "nbytes": 26894336, + "records": [ + { + "name": "model.layers.48.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.48.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.48.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.48.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.49.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.49.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.49.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + } + ], + "md5sum": "9c64cce4eb1c74b8ce4e8c067d48292f" + }, + { + "dataPath": "params_shard_279.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.50.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "4f51c7443c5e59addfcb12b1cedfc758" + }, + { + "dataPath": "params_shard_280.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "46b047dd894393bfe3ebc7975a8f6300" + }, + { + "dataPath": "params_shard_281.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "2bf780f2f4cb33cdc3f6c6710ab4f903" + }, + { + "dataPath": "params_shard_282.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.50.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "9685b8c6b70b4b8fb8ef03390cbab655" + }, + { + "dataPath": "params_shard_283.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "8ce136332b8b005371dbeb769d31102b" + }, + { + "dataPath": "params_shard_284.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.51.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "8154a1737f37b763d19a1e60c418e5ff" + }, + { + "dataPath": "params_shard_285.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.49.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.49.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.50.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.50.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.50.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.50.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.50.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + }, + { + "name": "model.layers.51.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "f55bfabe23581f94c5de9c33f1522a2a" + }, + { + "dataPath": "params_shard_286.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "acdb51a29bf66483dde9781dfd7b85a0" + }, + { + "dataPath": "params_shard_287.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "11ad27b2185ad02f415feff8e6303fa8" + }, + { + "dataPath": "params_shard_288.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.51.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "1cdb1412e2ce4c7b8bba815c03eaff77" + }, + { + "dataPath": "params_shard_289.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.51.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "a9ad990c9a52e4c00a7d3662a9a5d06c" + }, + { + "dataPath": "params_shard_290.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.52.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "5a4b7c6089b5b111be03caa6ea4677b3" + }, + { + "dataPath": "params_shard_291.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.52.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "f8e274dbe29e974b2e9cf51ff8a735fa" + }, + { + "dataPath": "params_shard_292.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.52.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "aa892d3765b6ebfe8e9e2cae20d2812a" + }, + { + "dataPath": "params_shard_293.bin", + "format": "raw-shard", + "nbytes": 26894336, + "records": [ + { + "name": "model.layers.51.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.51.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.51.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.51.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.52.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.52.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.52.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + } + ], + "md5sum": "7e3cb69bfd83f38640c1eae677a22426" + }, + { + "dataPath": "params_shard_294.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "b9b7f69a5ae65657206863cc8fbc4d9f" + }, + { + "dataPath": "params_shard_295.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "0ec0451b875b27e4ce8a0708ca6691d9" + }, + { + "dataPath": "params_shard_296.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.53.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "20162e938ba0ddfe37c4597c1446c591" + }, + { + "dataPath": "params_shard_297.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "e1bbe928661cd2d9562e0268e268380d" + }, + { + "dataPath": "params_shard_298.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "f2046e1d2adb2b3267c2be353c13a552" + }, + { + "dataPath": "params_shard_299.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.53.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "22fa10f67dddc0b24418a395d533cb72" + }, + { + "dataPath": "params_shard_300.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.53.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "4c58fdb1fefa97e4984870eeafd17e9e" + }, + { + "dataPath": "params_shard_301.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.54.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "d44381a1f45fba48ca93e8dc43817db0" + }, + { + "dataPath": "params_shard_302.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.52.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.52.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.53.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.53.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.53.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.53.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.53.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + } + ], + "md5sum": "77e6339aa17c3cc637270f9295ac70f2" + }, + { + "dataPath": "params_shard_303.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "b10f6cd38681d2a827498930e00ab029" + }, + { + "dataPath": "params_shard_304.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "73a0b12e439c60148bda2ecca41fba13" + }, + { + "dataPath": "params_shard_305.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.54.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "0f28775556181278ff2e5af27d7eebc3" + }, + { + "dataPath": "params_shard_306.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.54.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "06fb7d329287f0ee0a3a5d8cb83ce2a3" + }, + { + "dataPath": "params_shard_307.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.55.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "f4b0fe3b05d1292a687285162d2514b5" + }, + { + "dataPath": "params_shard_308.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "f9eb170211227fc9a1774e77104250c6" + }, + { + "dataPath": "params_shard_309.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "c600a9a7cbe197a5f66b0095f52173ff" + }, + { + "dataPath": "params_shard_310.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.55.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "d83318ae3142e5e32b3694b7effa455d" + }, + { + "dataPath": "params_shard_311.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.54.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.54.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11747328 + }, + { + "name": "model.layers.54.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15945728 + }, + { + "name": "model.layers.54.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19304448 + }, + { + "name": "model.layers.54.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.55.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19337216 + }, + { + "name": "model.layers.55.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19353600 + }, + { + "name": "model.layers.55.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "a43f43b5b83738ad4fb29e98d3668a0a" + }, + { + "dataPath": "params_shard_312.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.55.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.55.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "9970d3a94981ee2102773e43f39583bf" + }, + { + "dataPath": "params_shard_313.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.56.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "2a05952e89d570f9c865798923611167" + }, + { + "dataPath": "params_shard_314.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "359b846bf797be212bd510dc4ff138c0" + }, + { + "dataPath": "params_shard_315.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "4eb07dc343e1df4432501278cb0c6ec4" + }, + { + "dataPath": "params_shard_316.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.56.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "d75c0ed2c1c256d014e5cfc33241b10c" + }, + { + "dataPath": "params_shard_317.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.56.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "af3d27f04a2431bbe94240dea9a43c6f" + }, + { + "dataPath": "params_shard_318.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "78e6661edf7a496561faac43edc47211" + }, + { + "dataPath": "params_shard_319.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "1516eb21f86d6d2b8a2aec1f2e7217f7" + }, + { + "dataPath": "params_shard_320.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.57.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "9b041a06f3ec81427c23c1f5cb978cfa" + }, + { + "dataPath": "params_shard_321.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.57.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "ed529bad3bda86b0443f8ea7707e2ef6" + }, + { + "dataPath": "params_shard_322.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.57.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "eeb9d15676b5e8c3ddd7c4dfac95c818" + }, + { + "dataPath": "params_shard_323.bin", + "format": "raw-shard", + "nbytes": 30269440, + "records": [ + { + "name": "model.layers.55.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.56.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.56.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3375104 + }, + { + "name": "model.layers.56.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15122432 + }, + { + "name": "model.layers.56.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15138816 + }, + { + "name": "model.layers.56.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19337216 + }, + { + "name": "model.layers.57.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 22695936 + }, + { + "name": "model.layers.57.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 26894336 + }, + { + "name": "model.layers.57.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 30253056 + } + ], + "md5sum": "320147bea977291a68437cef2ab084c0" + }, + { + "dataPath": "params_shard_324.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.58.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "bce55e7da92f4ddfcd1ee38d4e2f993c" + }, + { + "dataPath": "params_shard_325.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "ca091f72562ed17d4637610728d9dd69" + }, + { + "dataPath": "params_shard_326.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "41e91a22ddcc4649349cfcb2bd60c655" + }, + { + "dataPath": "params_shard_327.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.58.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "875b88aa4df13253307053fd9baa3b71" + }, + { + "dataPath": "params_shard_328.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.58.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "79e764566bb26109634bcce73b088352" + }, + { + "dataPath": "params_shard_329.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.59.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "0919aa066ca2688627da76b9a2e76d33" + }, + { + "dataPath": "params_shard_330.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.57.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.57.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.58.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.58.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.58.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.58.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.58.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + }, + { + "name": "model.layers.59.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "95e0d1345398eea919c547fed51ccf39" + }, + { + "dataPath": "params_shard_331.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "13f5eba5251994ee8b261bcc7365965f" + }, + { + "dataPath": "params_shard_332.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "e8803123539bf626806cbcc4ad41743e" + }, + { + "dataPath": "params_shard_333.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.59.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "9213d54e92751f5f50de1d53c02e49e5" + }, + { + "dataPath": "params_shard_334.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.59.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "1d627c01cd227cc78720ab95882ed86b" + }, + { + "dataPath": "params_shard_335.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.60.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "effe422fecae602b3523aca16df83391" + }, + { + "dataPath": "params_shard_336.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.60.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "410a61d91efec5948d0dd8c6a0a05472" + }, + { + "dataPath": "params_shard_337.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "4e38fda004498b93f9ef411847789831" + }, + { + "dataPath": "params_shard_338.bin", + "format": "raw-shard", + "nbytes": 26927104, + "records": [ + { + "name": "model.layers.59.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.59.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.59.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.59.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.60.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.60.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26894336 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26910720 + } + ], + "md5sum": "a1349e24d3cffd6745f1302736d16a88" + }, + { + "dataPath": "params_shard_339.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "2c9743fa8c2a82b3d9090a2cd77e0c4b" + }, + { + "dataPath": "params_shard_340.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "91fed6ece50f733b9beea3e1827698ba" + }, + { + "dataPath": "params_shard_341.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "ec848631963df6bf1774c314b8b2341f" + }, + { + "dataPath": "params_shard_342.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "e2e646fbe31b359acb4972785297dd1e" + }, + { + "dataPath": "params_shard_343.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "a6e419b22b58af8c63d69ba7cf51a536" + }, + { + "dataPath": "params_shard_344.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "8b79f5984674924c6603cff75a0219e2" + }, + { + "dataPath": "params_shard_345.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "bbfc584475d59de7df745def0b2e0c40" + }, + { + "dataPath": "params_shard_346.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "7f78185427ff9f3c2411d295fa073d88" + }, + { + "dataPath": "params_shard_347.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19337216 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31084544 + } + ], + "md5sum": "d39edb6593184a159ed3818e7660aaa6" + }, + { + "dataPath": "params_shard_348.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "0a36e5c07cb1799319dae7e3ec70fd44" + }, + { + "dataPath": "params_shard_349.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "65d6597ad21ae6a97a5e7450403a6601" + }, + { + "dataPath": "params_shard_350.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "2afa947eda45e33d866bf257832a53bf" + }, + { + "dataPath": "params_shard_351.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.60.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "49e7bd6edde5edff7e43cc437e1ffafa" + }, + { + "dataPath": "params_shard_352.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "e544714c3210248085aba2aaa91da118" + }, + { + "dataPath": "params_shard_353.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "058bb8e9eed84f9bc56d66119911a3a5" + }, + { + "dataPath": "params_shard_354.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.61.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "812d197dd39b3dfb2bd6faa7b16cad38" + }, + { + "dataPath": "params_shard_355.bin", + "format": "raw-shard", + "nbytes": 22712320, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 3358720 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 7557120 + }, + { + "name": "model.layers.60.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 10915840 + }, + { + "name": "model.layers.60.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 10932224 + }, + { + "name": "model.layers.60.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22679552 + }, + { + "name": "model.layers.61.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22695936 + } + ], + "md5sum": "e6da5734d321b723c2e7923f256cc796" + }, + { + "dataPath": "params_shard_356.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "6368fa47de72b8d5aca15bd418143ba4" + }, + { + "dataPath": "params_shard_357.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "e7317b14a9cd2705c42bafdbbe55b4fa" + }, + { + "dataPath": "params_shard_358.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.61.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "a14ba0727d6c0234516505864bbb7d69" + }, + { + "dataPath": "params_shard_359.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "fed28e78cb763d062d71eaf0975ffe93" + }, + { + "dataPath": "params_shard_360.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.62.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "9ceb7b039afaa52c86569ed5bb42850e" + }, + { + "dataPath": "params_shard_361.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "e9af1ddecc4d2fcf95f01fc92cf59fa8" + }, + { + "dataPath": "params_shard_362.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "79dc540aa2dda7c3fb6a02523c055b2c" + }, + { + "dataPath": "params_shard_363.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.62.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "5e3a25f980f03c6a6205281b1947bfde" + }, + { + "dataPath": "params_shard_364.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.61.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.61.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.61.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.61.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.62.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19320832 + } + ], + "md5sum": "bf5548a916b36a9cafb229f9768a41a8" + }, + { + "dataPath": "params_shard_365.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.62.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.62.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "47781a3124edad6b64fe44ecff298c60" + }, + { + "dataPath": "params_shard_366.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.63.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "7b782de40184a86ca1b6ba91a7421b49" + }, + { + "dataPath": "params_shard_367.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "a5784a2394c0f662502412ee7a5531ef" + }, + { + "dataPath": "params_shard_368.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "3dc573c148e0df048e81a49266e23ebd" + }, + { + "dataPath": "params_shard_369.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.63.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "6e7819d0c474f844f9f72865e3a9d3e6" + }, + { + "dataPath": "params_shard_370.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.63.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "43d758126fea20d27b83f661afd6ff17" + }, + { + "dataPath": "params_shard_371.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.64.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "0355100cf6e5f9c9f462823279f24a06" + }, + { + "dataPath": "params_shard_372.bin", + "format": "raw-shard", + "nbytes": 22745088, + "records": [ + { + "name": "model.layers.62.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.62.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.62.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3375104 + }, + { + "name": "model.layers.63.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3391488 + }, + { + "name": "model.layers.63.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3407872 + }, + { + "name": "model.layers.63.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15155200 + }, + { + "name": "model.layers.63.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15171584 + }, + { + "name": "model.layers.63.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19369984 + }, + { + "name": "model.layers.64.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22728704 + } + ], + "md5sum": "25b1f83542cfe71b923616ba5ecd6ccc" + }, + { + "dataPath": "params_shard_373.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "cddf81b9e70a953ab71c98e17cd541a4" + }, + { + "dataPath": "params_shard_374.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "194cd19f107f89977b6e056b07247ba8" + }, + { + "dataPath": "params_shard_375.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.64.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "3b1037c7c6ccb2d5c39f645f47590ad1" + }, + { + "dataPath": "params_shard_376.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.64.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "cbf898721b8b96077a016781be23977c" + }, + { + "dataPath": "params_shard_377.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.65.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "e258d9ae43d3f1738e7b1b53ee726998" + }, + { + "dataPath": "params_shard_378.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.65.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "04e3b40d32a82975f5901f103811c497" + }, + { + "dataPath": "params_shard_379.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.65.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "85813b387026bee903907c69097dc3f6" + }, + { + "dataPath": "params_shard_380.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.65.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "7d5647dc050add82c832614aba450a37" + }, + { + "dataPath": "params_shard_381.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.65.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "eb095695be98aaf702892ac504ed04b4" + }, + { + "dataPath": "params_shard_382.bin", + "format": "raw-shard", + "nbytes": 26894336, + "records": [ + { + "name": "model.layers.64.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.64.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.64.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.64.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.65.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.65.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.65.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + } + ], + "md5sum": "cdf436e69472c1efe739302f5af533b5" + }, + { + "dataPath": "params_shard_383.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.66.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "e285877d427542a3223f0fff094a0611" + }, + { + "dataPath": "params_shard_384.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "fb7d6168627d4a0d677b3a1af2ca59b7" + }, + { + "dataPath": "params_shard_385.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "a8ff5c38939c1ca75f104dab192176c3" + }, + { + "dataPath": "params_shard_386.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.66.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "511bac2621c89f6790de328d3e4bda40" + }, + { + "dataPath": "params_shard_387.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.66.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "604f1f6964c0d035813675d2f8243f9c" + }, + { + "dataPath": "params_shard_388.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.67.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "be173a3bbc490f253574cb439d45e4f7" + }, + { + "dataPath": "params_shard_389.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.65.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.65.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.66.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.66.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.66.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.66.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.66.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + }, + { + "name": "model.layers.67.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "aa8b15975fcdf9179db1c90fcf635cca" + }, + { + "dataPath": "params_shard_390.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.67.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "4c1ff6770c64020e2c3d96e828a3d92a" + }, + { + "dataPath": "params_shard_391.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.67.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "25152fccc270abe9fdd33393c36bbb03" + }, + { + "dataPath": "params_shard_392.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.67.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "968cb2008b553467e77567c83f869cf0" + }, + { + "dataPath": "params_shard_393.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.67.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "c1aa18d04af06573afbeaf1c1e389c73" + }, + { + "dataPath": "params_shard_394.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.68.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "436e12eaca43343d3631aba08a7d07ba" + }, + { + "dataPath": "params_shard_395.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.68.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "b1e7a8b5f3f2773b13498e2c50196df9" + }, + { + "dataPath": "params_shard_396.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.68.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "15cb223ac54da1f53e44421388bc2edb" + }, + { + "dataPath": "params_shard_397.bin", + "format": "raw-shard", + "nbytes": 26894336, + "records": [ + { + "name": "model.layers.67.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.67.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.67.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.67.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.68.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.68.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.68.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + } + ], + "md5sum": "0af081eb4c4ad14b3e38bd161ce99739" + }, + { + "dataPath": "params_shard_398.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "8357cbb706b09d47d2fcf06800688fd0" + }, + { + "dataPath": "params_shard_399.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "a7975b912a1c3b94fb0ee84fd2484566" + }, + { + "dataPath": "params_shard_400.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.69.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "0908cc7c8d6a3a10c605cab9082fc1a5" + }, + { + "dataPath": "params_shard_401.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.69.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "2a60ccafa76ebec17a1eaae3c7f289ee" + }, + { + "dataPath": "params_shard_402.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.69.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "1f9ee53cf3be56bd0dde38fb33709f6e" + }, + { + "dataPath": "params_shard_403.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.69.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "99218c66b68e2656bf6ee09a2fd663fb" + }, + { + "dataPath": "params_shard_404.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.69.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "3f195635e72502fd9252c93b6cb81bd5" + }, + { + "dataPath": "params_shard_405.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.70.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "55e5eb44ab73f15f767b6647b23fd126" + }, + { + "dataPath": "params_shard_406.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.68.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.68.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.69.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.69.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.69.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.69.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.69.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + } + ], + "md5sum": "bc1a0e2e0e39188c2ffdd1fb62707990" + }, + { + "dataPath": "params_shard_407.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "60c5fb586023808a2a61a4b5152a499d" + }, + { + "dataPath": "params_shard_408.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "15187d9eb29f60c3b2459193101b2506" + }, + { + "dataPath": "params_shard_409.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.70.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "e6cff85f1f8977466bcf128c04bc4b2a" + }, + { + "dataPath": "params_shard_410.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.70.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "2abfb7f45324410598037f594ccf8f0f" + }, + { + "dataPath": "params_shard_411.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.71.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "79eda8f8444f1c2d5a2d427239ab7686" + }, + { + "dataPath": "params_shard_412.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.71.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "d3601a44dbf3d75a427d880f98f0f115" + }, + { + "dataPath": "params_shard_413.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.71.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "400f481857884b233d9e634a7a04d025" + }, + { + "dataPath": "params_shard_414.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.71.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "64702a4d6e707953d47740a0b4b3c758" + }, + { + "dataPath": "params_shard_415.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.70.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.70.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11747328 + }, + { + "name": "model.layers.70.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15945728 + }, + { + "name": "model.layers.70.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19304448 + }, + { + "name": "model.layers.70.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19320832 + }, + { + "name": "model.layers.71.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19337216 + }, + { + "name": "model.layers.71.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 19353600 + }, + { + "name": "model.layers.71.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "08ebea87e8dbe64829d79a885ec7f7f0" + }, + { + "dataPath": "params_shard_416.bin", + "format": "raw-shard", + "nbytes": 31068160, + "records": [ + { + "name": "model.layers.71.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 0 + }, + { + "name": "model.layers.71.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 4198400 + } + ], + "md5sum": "13359b5f259485a6a60bdba98cab2f7a" + }, + { + "dataPath": "params_shard_417.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.72.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "58f75534c1a753ce7ac75495ae8a52e1" + }, + { + "dataPath": "params_shard_418.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.72.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "4c52fb77aeb1a398e42df4a9a6ec0f5f" + }, + { + "dataPath": "params_shard_419.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.72.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "a574212437991b1dad70d5c5635a0981" + }, + { + "dataPath": "params_shard_420.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.72.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "cfeea1a7f6e2e03799a65d27669c32ad" + }, + { + "dataPath": "params_shard_421.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.72.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "87fcb790797a469d2aff93cef9a79efe" + }, + { + "dataPath": "params_shard_422.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.73.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "343788f666c365f3d5725dcbe8dd5521" + }, + { + "dataPath": "params_shard_423.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.73.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "7bc512eaeb4fddef53bff008d3d511ec" + }, + { + "dataPath": "params_shard_424.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.73.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "807bf85bc70c0d4474f469d480330227" + }, + { + "dataPath": "params_shard_425.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.73.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "fde92c7d9433c52aed0d39e82a087e0d" + }, + { + "dataPath": "params_shard_426.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.73.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "9e4c17a84da9b163f58b3e8fd9d800ab" + }, + { + "dataPath": "params_shard_427.bin", + "format": "raw-shard", + "nbytes": 30269440, + "records": [ + { + "name": "model.layers.71.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 0 + }, + { + "name": "model.layers.72.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 3358720 + }, + { + "name": "model.layers.72.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 3375104 + }, + { + "name": "model.layers.72.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15122432 + }, + { + "name": "model.layers.72.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 15138816 + }, + { + "name": "model.layers.72.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 19337216 + }, + { + "name": "model.layers.73.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 22695936 + }, + { + "name": "model.layers.73.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 26894336 + }, + { + "name": "model.layers.73.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 30253056 + } + ], + "md5sum": "b0d537b1d73818ee00e2773655ad463c" + }, + { + "dataPath": "params_shard_428.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.74.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "dbd5c0bb1ea5eac63b5a24c0b3744828" + }, + { + "dataPath": "params_shard_429.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.74.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "8f356bb3e20f5debc4ebfded297b3be9" + }, + { + "dataPath": "params_shard_430.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.74.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "dce6e55d348420c64141be1d615074ef" + }, + { + "dataPath": "params_shard_431.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.74.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "4ac5f657571b636190618c6cc2703e9e" + }, + { + "dataPath": "params_shard_432.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.74.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "a10500dcb5043977b4673f5494da014d" + }, + { + "dataPath": "params_shard_433.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.75.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "c2a514fa1e171bb7224059aab76637c3" + }, + { + "dataPath": "params_shard_434.bin", + "format": "raw-shard", + "nbytes": 31117312, + "records": [ + { + "name": "model.layers.73.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.73.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.74.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.74.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.74.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.74.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.74.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + }, + { + "name": "model.layers.75.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31100928 + } + ], + "md5sum": "bcff9f385d4bd34ca7020c42f0310f1c" + }, + { + "dataPath": "params_shard_435.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "491af6d8af9c23ae0825d8dc482f783a" + }, + { + "dataPath": "params_shard_436.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "abd097983e0aa5a7cc68894dfdd15c4f" + }, + { + "dataPath": "params_shard_437.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.75.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "84b047ed8eea73037ad591091598ba42" + }, + { + "dataPath": "params_shard_438.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.75.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "8e8ed0ee7c7b4880c1814b547239ee28" + }, + { + "dataPath": "params_shard_439.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.76.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "fa6a1d3fea315699a65d572812b4cc83" + }, + { + "dataPath": "params_shard_440.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.76.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "3793d80c77a73d12cc83eeeee9c04926" + }, + { + "dataPath": "params_shard_441.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.76.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "bf06cc235143de15366df98d3113bd46" + }, + { + "dataPath": "params_shard_442.bin", + "format": "raw-shard", + "nbytes": 26894336, + "records": [ + { + "name": "model.layers.75.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.75.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.75.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11763712 + }, + { + "name": "model.layers.75.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15962112 + }, + { + "name": "model.layers.76.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 19320832 + }, + { + "name": "model.layers.76.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 23519232 + }, + { + "name": "model.layers.76.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26877952 + } + ], + "md5sum": "fba64d8a7333d061c752984ecc99cdee" + }, + { + "dataPath": "params_shard_443.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.76.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "931dd93be1ec01d44ac5de77f7a4360d" + }, + { + "dataPath": "params_shard_444.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.76.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "a8ee458d797e61354aa5ffa9625c7c6f" + }, + { + "dataPath": "params_shard_445.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.77.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "903f3b4ee73c77101eac09680c977e1e" + }, + { + "dataPath": "params_shard_446.bin", + "format": "raw-shard", + "nbytes": 188088320, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 188088320, + "byteOffset": 0 + } + ], + "md5sum": "5a9dccdf1ec6d39ca4d98b6c0fa3fd45" + }, + { + "dataPath": "params_shard_447.bin", + "format": "raw-shard", + "nbytes": 23511040, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 23511040, + "byteOffset": 0 + } + ], + "md5sum": "863440e5c3aad8a9f50d2d60f1628d63" + }, + { + "dataPath": "params_shard_448.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.77.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "b40dc06faac1c1909d29088df526d7e3" + }, + { + "dataPath": "params_shard_449.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.77.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "cc2512bbdc8b6ad3be036f8b69b0da92" + }, + { + "dataPath": "params_shard_450.bin", + "format": "raw-shard", + "nbytes": 93978624, + "records": [ + { + "name": "model.layers.78.mlp.down_proj.q_weight", + "shape": [ + 8192, + 2868 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 93978624, + "byteOffset": 0 + } + ], + "md5sum": "eab016ae7a2fc3d794217ef409ceedd3" + }, + { + "dataPath": "params_shard_451.bin", + "format": "raw-shard", + "nbytes": 31100928, + "records": [ + { + "name": "model.layers.76.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.76.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11747328 + }, + { + "name": "model.layers.77.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11763712 + }, + { + "name": "model.layers.77.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 11780096 + }, + { + "name": "model.layers.77.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23527424 + }, + { + "name": "model.layers.77.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 23543808 + }, + { + "name": "model.layers.77.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 27742208 + } + ], + "md5sum": "ccea116d54228efa1968e131814a2a6f" + }, + { + "dataPath": "params_shard_452.bin", + "format": "raw-shard", + "nbytes": 33587200, + "records": [ + { + "name": "model.layers.78.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33587200, + "byteOffset": 0 + } + ], + "md5sum": "bec8028611f5f753ab1237558b5cf5dd" + }, + { + "dataPath": "params_shard_453.bin", + "format": "raw-shard", + "nbytes": 26869760, + "records": [ + { + "name": "model.layers.78.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 820 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 26869760, + "byteOffset": 0 + } + ], + "md5sum": "7d2af1d5b2fc2f0aba23d778e2297904" + }, + { + "dataPath": "params_shard_454.bin", + "format": "raw-shard", + "nbytes": 19304448, + "records": [ + { + "name": "model.layers.78.mlp.down_proj.q_scale", + "shape": [ + 8192, + 717 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 11747328, + "byteOffset": 0 + }, + { + "name": "model.layers.78.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4198400, + "byteOffset": 11747328 + }, + { + "name": "model.layers.78.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 205 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3358720, + "byteOffset": 15945728 + } + ], + "md5sum": "cbcb1ca06eb5395e065f45ee2433b1a7" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..7219d934f24a7187380f029465fed490dd173f73 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751eba367cbf012bf7e4a9ab697beae7ffc0ba312c529864f72b5fedc0efd35d +size 420679680 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..4239db0235c935df6d07cd25b3e89ce1ad4978f6 --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a9980127b43eebfdd70d930bfd607cf5409f1a22a4db38595cbcfa4f9a6b036 +size 52584960 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..484422f04df7e20b090feaf0787dacb9c895e442 --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f6ab8d9b78b99b66f153b5d515ff666ad5871e2fed833fcdbfa1960bdba233 +size 52584960 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f022e8523f9e9291017b12cc36b9c079448f2e2 --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b787a6e8a0a2434b94ae732041e3dd11e859315b5eb047ce0f3a3f7e92cd75a7 +size 23511040 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..e265f6d1040303a450399c9352b5c80647607339 --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75119db67030c11b58411cccb395f711da581bc07cb7e81a5afe0de668087a +size 93978624 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..42fb0dd3e2e9d1bc11eae759fbb88c6f2a525a7c --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:268c3ef9411784f5e54825f654c19e2e3a97e756d3f3395e67a9e5b0cd1232cb +size 188088320 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..59b26a5facd3df0cdfe364d265bdeef334ab2fc1 --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7bc7a17234100ea59040f59764f4cfc535dd810091c14a1156536cd29882183 +size 23511040 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..3ad9546d54ffb5b3cf0ff40943d93248b24cc741 --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80af00dc9749200174b255b6d526b48502b0069c221cea3b03f09fbe57048b4 +size 33587200 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc434e87c043d4ebd33e64fd89fd0e9c4bc02fb0 --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98090d07d435df7e28512bf4f562e0b166de88d8e21d8a4574c62a76d852992a +size 26869760 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..c97ec421f2d027d55ccd40f933a84ec23ee6f8d2 --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00abf0493708b9df170a75dd5a08644a7b441b44f86d658d251abe8a589878b1 +size 93978624 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e396b568e156316969921fbe553421100573a0f --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6847511e5e05abd8a313512e4c3982722aa35f1fdfe8cec565323195aa6c96f +size 31100928 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..d7efa3f83fdef44197324f15c3a28e96d1cf4930 --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e568a2a0d16c1e52ad054f6f9117fbb262e9124732740319d3989aae73f11aeb +size 188088320 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d8d4f86beb532667e80f5037ef8f7d285160ec1 --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c97c1ea76ca5dbfd7696370c1ae563b6d78d130157f3647067f8a285b161b199 +size 23511040 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..12d81aa4f9ff15835d3e8cab77126afb8642584e --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8961dd987c1ff36c86b82a174e62740b8067844e949ef2cb1e78a107a44052a9 +size 93978624 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..efbda70c98dd4657bc56a4c580eab1376bc4e45f --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4cfd05fb279cff827f364350c2422a9a054a07868657d1889853fa86f094a2c +size 33587200 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..457184820ca4bb6d68aaa0d5ad42519a1265cc19 --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ba08ca7ab4fbd09ad66b870f8edd9d22ddd30e903fdc26819aec288da1eec0 +size 26869760 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..a1a10413cc3e1c2a65e469e3b43e0d3a32c4d192 --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43f52964fe03a59ccb689506fc6841efbe60e5456e625be47c7987dde478ea8 +size 93978624 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..20bedb56b2440bfaef46c8fc645b9c140c46c342 --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e27163273ac6928859a5bd94f28187058b3af57287b02c84102d10cbf140fb +size 188088320 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..87a6b4969d2a8689604b44b13fdb067f9fdb34fe --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d36a44eab92df334caffdbec3b8f82c409262a7cb6cdd888e9f0fa187f54c30d +size 23511040 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..9501a2b206e0f5950fb1f4d59ad1fbb3fa5c3c6d --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437fe9315625b7ad53b4e5c99f7befda4453e5fefa2011db71d3f7b1c5670411 +size 33587200 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..cde088512bd6b46b85caa1ed7fe32139aa8dc0c4 --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ae0a7a047c57babebdf7d6527b62552267e1b5c81bc5829d1af5914033a236 +size 31117312 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a6a73771090655fde3aee2e24a3e99cda11457b --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2163a774a0adfa83853af3bc2e7f56769690ab0986701767be35682ce27a2f70 +size 31068160 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..d4f7f223f2475e2cfaf071ee128cdb3e0fc418c1 --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f7ef63e43ce112742d3b6e26281d6ea3e4fe755a17c60737cfa9c89136337c +size 93978624 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..92d29c72bc90629087c8d52aae0ca445b0022785 --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be3d3701e10a79d8495de8077837c17e6f6083f02902086eb4e8f9b51bb7be3 +size 188088320 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a9bf6455432306c142220b3eaf917b9cae5e574 --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551d0c1b649ef7f42ae3b8a65d2ef9ff7ade083f95705a744e64f5e55a0e92bd +size 188088320 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..4506a40f274e18b08e680275d49bfc3d8f84952e --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3b38ea0966451bbb7e9b20614ae404cabdcbe3f61c40c382ff269a3d1eede5 +size 23511040 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc149652a87be8f057962adf3687d452af4f2e2d --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503292dd41610dce4c1e3f91b335c770305cd65719f05e69ad4509afb0feee5c +size 33587200 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec4533e8a6afa8c2b086fed51f3245964b53f980 --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f73b62eba08b1f973444608c7e1edefcc138a7aa01074068f53b8498474776 +size 26869760 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..25743492bc79021cc93d5d53d1dc4d581721b73c --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b52fc8dba31fae6cbd24eecbe676ca38447ba23cf2a3db9e59a2411762f6c5 +size 188088320 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e5352a08a7cdadccb1400e10171c94f14103f52 --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aad125070889099f10533139d5c422b0cedae0a003e8644b3d9c04bbe5b59855 +size 23511040 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..388a8d1693d14fca19cf3443add83d05d23a9062 --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64673d14e7f1d37dc2c0df6651e0a98199353bdaf9c4e7efcea90cde623e5a3 +size 33587200 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..3999dc1189c3981d2c0fd388bed376d8daa0301a --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2b2fbdf7a2fcd3bc57eac8af8d05de3cebc6a7d96e6910cb7b922ba54f4b23 +size 26869760 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..18cd19974ae98af43fca004772b7321feb4a90af --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16295cad04d47cd1513d3a924051fbbc7079d903f8f7b8514cfaac56c4aa52c6 +size 93978624 diff --git a/params_shard_128.bin b/params_shard_128.bin new file mode 100644 index 0000000000000000000000000000000000000000..34b5b8d5687d40cf3bac8358c749110d8ca246de --- /dev/null +++ b/params_shard_128.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:070d2d33bafc37ce9bac3c2c22ee3d30d1bfe8ebc1c167362327d75c35519458 +size 30269440 diff --git a/params_shard_129.bin b/params_shard_129.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ff7a396b1875f2b036084317593bcc9e142066d --- /dev/null +++ b/params_shard_129.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d4dd3afa1ea873eefb2a512c7af45d599486305a488b6059488a9af79f6f16 +size 93978624 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..faeca47820f7801ce2e6532a91831648f7f65182 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358bfbf7c85d29cd5f26fa23a96f7cd4da690331a1eb3b7316a324af407ac7e4 +size 23511040 diff --git a/params_shard_130.bin b/params_shard_130.bin new file mode 100644 index 0000000000000000000000000000000000000000..7739b9d580c7385984b2b3433289542e452634d6 --- /dev/null +++ b/params_shard_130.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4017590e01b75f8429bf08a14cd5714421b6e3a20ae3f96ff788a0cd41e9d0b6 +size 188088320 diff --git a/params_shard_131.bin b/params_shard_131.bin new file mode 100644 index 0000000000000000000000000000000000000000..13531b124bd62b07bd9650b326628c2d2c3ff17e --- /dev/null +++ b/params_shard_131.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49c15eb1f8bacb456ee732c948dcf69a3590274c775c153238fd7a58fae4bf1b +size 23511040 diff --git a/params_shard_132.bin b/params_shard_132.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc34b4690e2f363a4b85a1f6bb04094e3ab05947 --- /dev/null +++ b/params_shard_132.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6d832c510f30199770068ad2ec4b987e6d8d4086c051bd7e68567c9ed2bba3 +size 33587200 diff --git a/params_shard_133.bin b/params_shard_133.bin new file mode 100644 index 0000000000000000000000000000000000000000..42674aeffc4c986d407f6dca6dbf1b520f96eb05 --- /dev/null +++ b/params_shard_133.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3d548e4c47be1abed74ca3b8d5f5c7822cb4b2fdf311d268423370e1a1ce51 +size 26869760 diff --git a/params_shard_134.bin b/params_shard_134.bin new file mode 100644 index 0000000000000000000000000000000000000000..c550bf021d0e27338135be48b9188ad82bb1a5e4 --- /dev/null +++ b/params_shard_134.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1448389fa783c19b752cca333fa665b60608c176a03586ce0756d56da48d2155 +size 93978624 diff --git a/params_shard_135.bin b/params_shard_135.bin new file mode 100644 index 0000000000000000000000000000000000000000..ee6ab7273d24769775ad8c1adacd1c26d2f6631e --- /dev/null +++ b/params_shard_135.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f043295b06eece6b82787009dc381c6862f99a2fb7e77af4fe12dc7345d1a7 +size 31117312 diff --git a/params_shard_136.bin b/params_shard_136.bin new file mode 100644 index 0000000000000000000000000000000000000000..4906a0918677a8272eafc5a733e1eeb02d40dd6b --- /dev/null +++ b/params_shard_136.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e91203ef8d2e40d01ff385ebe93b1bb975d3885cb1268b97f1441e50c9913cd9 +size 188088320 diff --git a/params_shard_137.bin b/params_shard_137.bin new file mode 100644 index 0000000000000000000000000000000000000000..a13860595f848dccd035fdfe7e11b68839490940 --- /dev/null +++ b/params_shard_137.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b2eb30b180b94eb9c8f35c628de5e3bece7d887ee41c16fb6bc5e8523c7cd77 +size 23511040 diff --git a/params_shard_138.bin b/params_shard_138.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9c939d5963fa697ed79e0dffa4e938659f25cc8 --- /dev/null +++ b/params_shard_138.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b19aa03a999a9c2f0ec71def8f41c3181e7aea3662fdeeb521b9ecc0c6e7edf +size 33587200 diff --git a/params_shard_139.bin b/params_shard_139.bin new file mode 100644 index 0000000000000000000000000000000000000000..375660a161e0485ddc266b26db36b7ac5518f486 --- /dev/null +++ b/params_shard_139.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d331ab53f4b6c5d8c1232357cde981241e3d5beef59fa6e5f8669842ee71423 +size 26869760 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..05e63580b11242cec8a8133147762f9d24163cef --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d206312798b08992ff61da3ca4f139708a5b77c21f58a8bb6a28c40bbad18fce +size 33587200 diff --git a/params_shard_140.bin b/params_shard_140.bin new file mode 100644 index 0000000000000000000000000000000000000000..adf9e3c85c53186badf336dfe64192216b865054 --- /dev/null +++ b/params_shard_140.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c65f03b870aacb42cc577db0a34df76c9abb14a9320611418ed5f14f2afa974 +size 33587200 diff --git a/params_shard_141.bin b/params_shard_141.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d60de3fc36b8130038d15a6641c2cf596a46a6b --- /dev/null +++ b/params_shard_141.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699a6d219502fa377f609154278f410fbe01a8eea8119f4ce2e195632bff60cb +size 26869760 diff --git a/params_shard_142.bin b/params_shard_142.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d7906ee2dbb26c3403348e36d1e930e4b164782 --- /dev/null +++ b/params_shard_142.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48c84fb109c3abf8159e3777f9ec91a87ced1f7f091bc9e88b87686d07695a2 +size 93978624 diff --git a/params_shard_143.bin b/params_shard_143.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed6667a7148d47492aef7d1a0cba049551704269 --- /dev/null +++ b/params_shard_143.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2430d00c33d55cd861eea46fb64632e02f99035162dc7ba3fe9ae464c48524ac +size 26894336 diff --git a/params_shard_144.bin b/params_shard_144.bin new file mode 100644 index 0000000000000000000000000000000000000000..a44846dd69f6f32568d4171c054c3fffb8dfb3cd --- /dev/null +++ b/params_shard_144.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5bb51f3c83eab5f2c196d2816320c14d297add6489d388edb98ada8a00cebf0 +size 188088320 diff --git a/params_shard_145.bin b/params_shard_145.bin new file mode 100644 index 0000000000000000000000000000000000000000..91201e23f95146c234ee6e1f3deea33d9d43b3dd --- /dev/null +++ b/params_shard_145.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa1b70b11d3f36354ad6ba0a8205bcebd8c8618626973f1abbdb5e8db60368db +size 23511040 diff --git a/params_shard_146.bin b/params_shard_146.bin new file mode 100644 index 0000000000000000000000000000000000000000..d524972b2b3405cf3106e9b650aefca46dc00cf1 --- /dev/null +++ b/params_shard_146.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c8b2fe2a54ac7a0b4e1dfd5dc1031dfa7d0f40e7781466311eb789f935903e +size 93978624 diff --git a/params_shard_147.bin b/params_shard_147.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed6c8f2202e06b436c9bbd1d2a11de427561b9d4 --- /dev/null +++ b/params_shard_147.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16220f4bd6ac75ea7f7b374d0b244b7d2e615bf5d169e1b07a4f8303f2d577b3 +size 188088320 diff --git a/params_shard_148.bin b/params_shard_148.bin new file mode 100644 index 0000000000000000000000000000000000000000..a0c156ab7895a6da40a21f53a069773f214f4a0e --- /dev/null +++ b/params_shard_148.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa07e7503793c97cdc05ea2408a867f25f2c7fb4f8638706ccefa10246d6100 +size 23511040 diff --git a/params_shard_149.bin b/params_shard_149.bin new file mode 100644 index 0000000000000000000000000000000000000000..156bc4e0f65f024a845a54556c39b778223b8bb5 --- /dev/null +++ b/params_shard_149.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180c58c980765779cc9e9e121788ac79f7fdcd64568a648d9a5d7a939c5dee61 +size 33587200 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ee42297714aefe2c5904c56e9fc8d023c468496 --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a229a61d7ff55e191f27623b31dcab97cfe9ac438d9ba30745857d240263fe87 +size 31117312 diff --git a/params_shard_150.bin b/params_shard_150.bin new file mode 100644 index 0000000000000000000000000000000000000000..1c567dd6f1a232ce1f7ec06452394ce0a6c71c74 --- /dev/null +++ b/params_shard_150.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3449db8846e6be9ac975c5cb8bc343c6f5fcb2b975f23975a68ec8077ad22335 +size 26869760 diff --git a/params_shard_151.bin b/params_shard_151.bin new file mode 100644 index 0000000000000000000000000000000000000000..edc8364fa10645ffff09bbc30468b5b4c270cbb7 --- /dev/null +++ b/params_shard_151.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf64eef47defcb682471bf40e97a6a7ae8fc6608be17aca7885e802b9e3821f +size 93978624 diff --git a/params_shard_152.bin b/params_shard_152.bin new file mode 100644 index 0000000000000000000000000000000000000000..4820a26cfba813e39b606f3cf7841c73017214c1 --- /dev/null +++ b/params_shard_152.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8022b8ec6701647432c90928362311254f2aa04c0d33506729e01c9dee0fb3a +size 31100928 diff --git a/params_shard_153.bin b/params_shard_153.bin new file mode 100644 index 0000000000000000000000000000000000000000..5fbf7acf9bec51e68e8c8d225c0e910fe2c81f11 --- /dev/null +++ b/params_shard_153.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104ae3fe82563e215977ee47a73427577e18c2dad3477c81fbf3ec1e55f652d0 +size 188088320 diff --git a/params_shard_154.bin b/params_shard_154.bin new file mode 100644 index 0000000000000000000000000000000000000000..285e82a660e0486ff5382da7b5a2a08e0512def9 --- /dev/null +++ b/params_shard_154.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4974bdf859c3aa74e6b42fce928e4b7be894827fd95db5f68f4347e4a94a2b2 +size 23511040 diff --git a/params_shard_155.bin b/params_shard_155.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b5cc9d27c7c105ee40062f56ee3afb8009ffdab --- /dev/null +++ b/params_shard_155.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4185d1a422575730ac6264c68eced1133c9a5e59927adf5b84216eafd63b3f83 +size 33587200 diff --git a/params_shard_156.bin b/params_shard_156.bin new file mode 100644 index 0000000000000000000000000000000000000000..1c37ef0940701ec69286fe30b4be6c34d5075b17 --- /dev/null +++ b/params_shard_156.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0440f5c4616d5ecfbc4d1a2fe8124c498700c542b4e4942f44b29096ea18d5 +size 26869760 diff --git a/params_shard_157.bin b/params_shard_157.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab6921d9e9e4a5732f91c17c0fda0f7258f7257d --- /dev/null +++ b/params_shard_157.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c31106c421f405dea88b514cbdf8b509c2ac3dda360432154d6ccf778d5a4e22 +size 93978624 diff --git a/params_shard_158.bin b/params_shard_158.bin new file mode 100644 index 0000000000000000000000000000000000000000..200f3105c290aa60fbd4d8b98b3062901af65d2e --- /dev/null +++ b/params_shard_158.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff17c57feb5f4b9472be66b17d6faf2ff2b336d0cea05e34961b88690f89bbed +size 188088320 diff --git a/params_shard_159.bin b/params_shard_159.bin new file mode 100644 index 0000000000000000000000000000000000000000..408e5d21f6999aabdd8b65b02690c8c268fb2c11 --- /dev/null +++ b/params_shard_159.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22632b1433ac3e35fcedf6380523c0d532bc85d5395a6e535b1fd793fd4161d +size 23511040 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..efa9327ed1299a9873f4c885c05f82736a8c7ea6 --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207b80e1c4adc32a774e73afe5e53b8b3c1dc15d8be1b40b533a0eb0dab3aef3 +size 31068160 diff --git a/params_shard_160.bin b/params_shard_160.bin new file mode 100644 index 0000000000000000000000000000000000000000..db1fd435e4beadcb4aaa1ac635bb6ecfe3f734f2 --- /dev/null +++ b/params_shard_160.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f061560da5aaa385656257c015259009764347ec6cecdffe1fb5c6bdf4d948be +size 33587200 diff --git a/params_shard_161.bin b/params_shard_161.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f9604f9cc676db7d4f0a6b7d1abb98f2a8209d2 --- /dev/null +++ b/params_shard_161.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99b9edabfbd1ce9ba7147ecd9a13dcb7340e8dbef7d55399c15dc7737b737276 +size 31117312 diff --git a/params_shard_162.bin b/params_shard_162.bin new file mode 100644 index 0000000000000000000000000000000000000000..d018e1bb4455a7b3eb316e672c6fb36e4e5c7415 --- /dev/null +++ b/params_shard_162.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aebf66eee0a6df133d749f8c9aeb3414ad57f85507cf191f9eaf7d9ae45802e5 +size 31068160 diff --git a/params_shard_163.bin b/params_shard_163.bin new file mode 100644 index 0000000000000000000000000000000000000000..05643bbb7a5adc925bb8d6ef628dc7dbd8cf94e3 --- /dev/null +++ b/params_shard_163.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27d2a2e0c7c8f7b62a70fc43250ce62c5cd762cbf75c08f37b1559007edf8bd +size 93978624 diff --git a/params_shard_164.bin b/params_shard_164.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f7ef1bec7aaf567754137f3eff97a3959beea6d --- /dev/null +++ b/params_shard_164.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfabc26366b0d2da6db65e257fd335a5be8fd26de1db9b8f598f3ad91541640f +size 188088320 diff --git a/params_shard_165.bin b/params_shard_165.bin new file mode 100644 index 0000000000000000000000000000000000000000..73dae229fcaca37618988eadd7f15578e701e866 --- /dev/null +++ b/params_shard_165.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97325347510b9ec33998af855a44895e947e2a67f82fff88c61fe80e2b0e90a6 +size 23511040 diff --git a/params_shard_166.bin b/params_shard_166.bin new file mode 100644 index 0000000000000000000000000000000000000000..170b38ca30be17b9bc90c5afff6d98c3aac71ab5 --- /dev/null +++ b/params_shard_166.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d6267d88e5bf57c554c58995e0e3d7d3172850a83f2cb1ff7adbe1ca27961b +size 33587200 diff --git a/params_shard_167.bin b/params_shard_167.bin new file mode 100644 index 0000000000000000000000000000000000000000..5c19254b15b9f54838b4ce3ba9f8d60845dc8be5 --- /dev/null +++ b/params_shard_167.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:973c44ad1e70aead3c77374b14094bdb976ecc89f125d6e95d9cf75859e68073 +size 26869760 diff --git a/params_shard_168.bin b/params_shard_168.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c01760ecf71fc8934fbffdc57d29a636a9d55fa --- /dev/null +++ b/params_shard_168.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ebee01f8af77d1cafe2608c28277ff5e51663abf137284a52d9dca30980077 +size 188088320 diff --git a/params_shard_169.bin b/params_shard_169.bin new file mode 100644 index 0000000000000000000000000000000000000000..27d33bc669aba7b4569a16f05a0d4d3014285b1f --- /dev/null +++ b/params_shard_169.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe00a949456e9a0902752f0a70beb78bec19ad23dd6ac8de10135428da0c522 +size 23511040 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..0de324fc5e01a8c6462dc5872d2912cbd4c634a0 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84512f370d030eb2a20b663ab67ffd16bfec47c26f66a09055b184cf0155b1a +size 188088320 diff --git a/params_shard_170.bin b/params_shard_170.bin new file mode 100644 index 0000000000000000000000000000000000000000..c426a1ec8280d1f30a591c2919681af4535a7f9f --- /dev/null +++ b/params_shard_170.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acbe430d7a307d460e58b0473d2834684a96240b8b5dffc5f48b0fb73bdca53c +size 33587200 diff --git a/params_shard_171.bin b/params_shard_171.bin new file mode 100644 index 0000000000000000000000000000000000000000..3f99b676704ee369fe8a87a611da0b52695b75d0 --- /dev/null +++ b/params_shard_171.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2f6930e7d6655ec81a8f247fd40d08acc5f69cb9422b9dd0428b9edc59adb27 +size 26869760 diff --git a/params_shard_172.bin b/params_shard_172.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d9f8ea9f8d7e66c36174a1d4e804f49057d718a --- /dev/null +++ b/params_shard_172.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69fb190fb52800b259d7d42d43e2b4eb3988554208e97cc9a0970eb1b8edef69 +size 93978624 diff --git a/params_shard_173.bin b/params_shard_173.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a3ad31ec76b3c278b6e0a5665b00867bcb59515 --- /dev/null +++ b/params_shard_173.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ef6a4f958a26ce9aa2fcd8864c09cd51647137ea520be306b31125e4440800 +size 30269440 diff --git a/params_shard_174.bin b/params_shard_174.bin new file mode 100644 index 0000000000000000000000000000000000000000..8735ac22e0e90cd37ec1bc8063efe630ea691b36 --- /dev/null +++ b/params_shard_174.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38aec1b72a00f9ae52e2828ee39c24670523f8c610912ab4069fa615f699fec5 +size 93978624 diff --git a/params_shard_175.bin b/params_shard_175.bin new file mode 100644 index 0000000000000000000000000000000000000000..aeb3c65a638c493b74e0bf6d860fe7a866157459 --- /dev/null +++ b/params_shard_175.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f80251af281083063649e3fc3cc2dca04b19881bef14cd71131462b2336583e +size 188088320 diff --git a/params_shard_176.bin b/params_shard_176.bin new file mode 100644 index 0000000000000000000000000000000000000000..193b1b7e5a47bd941f00bd496e8c891abcba2517 --- /dev/null +++ b/params_shard_176.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f7bbb80a782d2178aab328290564409eb08a79f5209df360a08c435aa47f07 +size 23511040 diff --git a/params_shard_177.bin b/params_shard_177.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8c84980306d554a81fcb70696256764bc7078ad --- /dev/null +++ b/params_shard_177.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76850e9813e88eeba32c84686ba547f2437af0738c48ca07f340047191d874fa +size 33587200 diff --git a/params_shard_178.bin b/params_shard_178.bin new file mode 100644 index 0000000000000000000000000000000000000000..b15743d88326b97c6c1b5dad9d4d27da991d9369 --- /dev/null +++ b/params_shard_178.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:929360c3796099f0c36c208e07c03eb83eea86d7321dd854a0c87ffeec9abbac +size 26869760 diff --git a/params_shard_179.bin b/params_shard_179.bin new file mode 100644 index 0000000000000000000000000000000000000000..4645942f5b0ddba4b52fb49280342d92a7d7f105 --- /dev/null +++ b/params_shard_179.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f049c118d510da82af59065bf04e7250a12feb5cc36bd658012d923726e2f6 +size 93978624 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1b19582eacd145dcc8a266c17813ac31ace3d19 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b31015e7d53eb9390b37f87f9995481586c6349adde4079a580c8033834bd6 +size 33587200 diff --git a/params_shard_180.bin b/params_shard_180.bin new file mode 100644 index 0000000000000000000000000000000000000000..6c52b93999fa41dd9d1c1790e0cee85603bfe6e3 --- /dev/null +++ b/params_shard_180.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d92db7513d33c56a619679b2c97bc4641c9c4dc1aeb25e5c7268479dc4ed953 +size 31117312 diff --git a/params_shard_181.bin b/params_shard_181.bin new file mode 100644 index 0000000000000000000000000000000000000000..45d05269d2b4af4f49acad232d66f38ca6c7b4dd --- /dev/null +++ b/params_shard_181.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d3cbdf98b22d99564a4c1bcb460769b20e139807813ce154c75116526b4439 +size 188088320 diff --git a/params_shard_182.bin b/params_shard_182.bin new file mode 100644 index 0000000000000000000000000000000000000000..c04239a8a7f4233a2295b2c24b1a7b2efce33c46 --- /dev/null +++ b/params_shard_182.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94add4bfd79f89436bbbf49a254e39f3ec5b0ba5d11f2a948ff1d406f1fb7b22 +size 23511040 diff --git a/params_shard_183.bin b/params_shard_183.bin new file mode 100644 index 0000000000000000000000000000000000000000..56702f17479bbd5ba00dfbdf428c0fe5e2fd6964 --- /dev/null +++ b/params_shard_183.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b14ebf647da473328b9ccac37cfa8d4b2ae5ccae9d10365d0154ce0df24bc24 +size 33587200 diff --git a/params_shard_184.bin b/params_shard_184.bin new file mode 100644 index 0000000000000000000000000000000000000000..10fda7d113b2115530119199909e93ca2bcff0cd --- /dev/null +++ b/params_shard_184.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f23111a2a867cc38baa40be0cfb28817b4e0fec8dcdaaae1786bf148678e06 +size 26869760 diff --git a/params_shard_185.bin b/params_shard_185.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1abbd6740c278e9e92bd2fdc81cc71fff06d986 --- /dev/null +++ b/params_shard_185.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f597115a86d9063566360cd5ef5cfb6d46c8aacbbba1a7c26f9e5d3f662538c +size 33587200 diff --git a/params_shard_186.bin b/params_shard_186.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd7a36195397128b850cc20fb1bada0e25c48ed9 --- /dev/null +++ b/params_shard_186.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a7b248e5edba2009a4ea50d2c3a4f6f0c2e454b2934d8d6b5b18bd9d90f34ea +size 26869760 diff --git a/params_shard_187.bin b/params_shard_187.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd9c33dee5e60a4aba71e367e90abcd13dbadb1b --- /dev/null +++ b/params_shard_187.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4603baf32bdefa5bd3e8a84f022d7702a24e7d6dacad0fa8f78db196b33358b +size 93978624 diff --git a/params_shard_188.bin b/params_shard_188.bin new file mode 100644 index 0000000000000000000000000000000000000000..a9e00fbed1900c79917338eda7f328896e20947c --- /dev/null +++ b/params_shard_188.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c7b067f0a6c6a50a1f1297afca2139c275cb0116f9ef9872fd73d2c9649694a +size 26894336 diff --git a/params_shard_189.bin b/params_shard_189.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d75f373409680da683bb00af0ecd150e54e7f65 --- /dev/null +++ b/params_shard_189.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca9ecfe336e51102b037a6514ca114d9137c0ea9bfe1a1c99f051ee5355f007 +size 188088320 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..8bc6836e8dab1ce1591446efbf73fb9c76fd035d --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac328379e428714a19089432009510f727af381c3226ea57214adb365c05af9 +size 26869760 diff --git a/params_shard_190.bin b/params_shard_190.bin new file mode 100644 index 0000000000000000000000000000000000000000..5623214afc6db08880ab96dff4be23ca1333594f --- /dev/null +++ b/params_shard_190.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5875b36aff66c102a488fff23af1c9c9e48f75e4a7655d9941942024530173 +size 23511040 diff --git a/params_shard_191.bin b/params_shard_191.bin new file mode 100644 index 0000000000000000000000000000000000000000..d6f9569b9f047b639fd7f9fa76b77fa0a25c5382 --- /dev/null +++ b/params_shard_191.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a63f67da87e838e5432179ef2ff4ac71fac0526371c24a8e16d402d79dc61a68 +size 93978624 diff --git a/params_shard_192.bin b/params_shard_192.bin new file mode 100644 index 0000000000000000000000000000000000000000..9965191225263505e94099c84cbe4673c843f71e --- /dev/null +++ b/params_shard_192.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6fea7f63dabffc4d776c1ecfed67e65d32ee89928b745dd7b6f3ce2119833f2 +size 188088320 diff --git a/params_shard_193.bin b/params_shard_193.bin new file mode 100644 index 0000000000000000000000000000000000000000..66be147c27655e102161da01f5c74b6994fa7187 --- /dev/null +++ b/params_shard_193.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c9f6967081e43fa1d1fa52703737937abca16bf6e8235c52e681d0873d69fc +size 23511040 diff --git a/params_shard_194.bin b/params_shard_194.bin new file mode 100644 index 0000000000000000000000000000000000000000..35d6e90c82d3fb856907acbf11d431eef37ce4d9 --- /dev/null +++ b/params_shard_194.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd149bc8bd2509aa874eeeb09bb6a5c133be8ae32992ca89f25b027fafe99466 +size 33587200 diff --git a/params_shard_195.bin b/params_shard_195.bin new file mode 100644 index 0000000000000000000000000000000000000000..76a4d0d87aa6c70c3202263d577be3df47620e9d --- /dev/null +++ b/params_shard_195.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7a2291a9da47808906a08fe574f44e498bc6f4f0f06564c2fd42c1deca970a +size 26869760 diff --git a/params_shard_196.bin b/params_shard_196.bin new file mode 100644 index 0000000000000000000000000000000000000000..c474db6950fafed254ddf2799a4136975bb76673 --- /dev/null +++ b/params_shard_196.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6ddb2f106d28934d0e64ea09d6ee778459dcfc9d0663f695922576942d8265b +size 93978624 diff --git a/params_shard_197.bin b/params_shard_197.bin new file mode 100644 index 0000000000000000000000000000000000000000..287e49d3f7514945dfb5c18cb6c7d45840689832 --- /dev/null +++ b/params_shard_197.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afde34800218709fcee7a4b4d05ebe630ca25880e0370d6dbd5a73534d1025fd +size 31100928 diff --git a/params_shard_198.bin b/params_shard_198.bin new file mode 100644 index 0000000000000000000000000000000000000000..dbb39f8d4da6e30c52ef13808562fb3e6c7288f1 --- /dev/null +++ b/params_shard_198.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca833de9208e848c557e751e2c18cf9b1be98d622754ca7a47a57b2824c3c60d +size 188088320 diff --git a/params_shard_199.bin b/params_shard_199.bin new file mode 100644 index 0000000000000000000000000000000000000000..9c4a396c8dba37f32664066c7723429984297790 --- /dev/null +++ b/params_shard_199.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949b731d1da4c140032f5c2bb2b15a87db97d464d68305cb928d4abfc36a114c +size 23511040 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..18244ba6a83c1d839fbc11a951c3ff4d96745b3b --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e248b3ff1b28235e6304cfcbcb91f5da938ceea3d115b2b4cbb714b03f8696 +size 188088320 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..59b33675f005f8c645327898b8e6471b674a7964 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d0ff3940a659f83d42e0ef613cb1516cdcd3b7153b6dbd5f672baeaf86ca263 +size 31068160 diff --git a/params_shard_200.bin b/params_shard_200.bin new file mode 100644 index 0000000000000000000000000000000000000000..58f6b8504a7814e48fde56dd78507f1db1e79f67 --- /dev/null +++ b/params_shard_200.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62c12af8114e3ab2dce71f9b775911b817e053ec0b116c32d64af952b93758c +size 33587200 diff --git a/params_shard_201.bin b/params_shard_201.bin new file mode 100644 index 0000000000000000000000000000000000000000..d89419012b7390358db9d5a0393fd69b652d72e7 --- /dev/null +++ b/params_shard_201.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b68f2fba663e87622ef091ef25a3740e303634269c7c15cd1265739cdc1bd3 +size 26869760 diff --git a/params_shard_202.bin b/params_shard_202.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc48b381f5d4a7e8bdddde0afb6bec3f38874787 --- /dev/null +++ b/params_shard_202.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d959a05aefc2c2abd630b2ab1500d993da1a4008f229345274fe7e023c9c9dd +size 93978624 diff --git a/params_shard_203.bin b/params_shard_203.bin new file mode 100644 index 0000000000000000000000000000000000000000..94f724efa07f2054f97f0870ceea9e356944c526 --- /dev/null +++ b/params_shard_203.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2073a12a7c79ac598559e186559faf928591a8442835aa555589a4f6f057b0 +size 188088320 diff --git a/params_shard_204.bin b/params_shard_204.bin new file mode 100644 index 0000000000000000000000000000000000000000..c313afeeaf56c18af7ef9009942a454b164c4a56 --- /dev/null +++ b/params_shard_204.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d0803f13a2476d2b1d059b23fb06967ae30e0ae71e6710dbeb38ed9124107b +size 23511040 diff --git a/params_shard_205.bin b/params_shard_205.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d9caa517f17a5504b45be40c7cc4183d4c6715a --- /dev/null +++ b/params_shard_205.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d87b7f175169ad2b45c3aa1ae3d6f93d17ca9f26ba6e6bfac739a9d185c78635 +size 33587200 diff --git a/params_shard_206.bin b/params_shard_206.bin new file mode 100644 index 0000000000000000000000000000000000000000..abd6871fc5dab7b3de7233fe4b3933690ba4aeae --- /dev/null +++ b/params_shard_206.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c284eb8c0c89d0b41f465f2c5a4868ec38a8c5819df4257504c1c349c7aac2ab +size 31117312 diff --git a/params_shard_207.bin b/params_shard_207.bin new file mode 100644 index 0000000000000000000000000000000000000000..23ad23b6395fc9e1842db959681291fd04f1dc3a --- /dev/null +++ b/params_shard_207.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3658c3740a1e724a910c61f3f0346452ff1e1b4e7c490b89a11e4546b32e7049 +size 31068160 diff --git a/params_shard_208.bin b/params_shard_208.bin new file mode 100644 index 0000000000000000000000000000000000000000..1be8fcbf479d4520b5557d3830917b516a6a0725 --- /dev/null +++ b/params_shard_208.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddcd2d6620cf5e015fe8ed8eb7d8d463be98ff4d5e6e4abb82a2ca9e85cbdebb +size 93978624 diff --git a/params_shard_209.bin b/params_shard_209.bin new file mode 100644 index 0000000000000000000000000000000000000000..b59174162df0f740d1488246a837bf552332d797 --- /dev/null +++ b/params_shard_209.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85c59a88aea672d3a487e35a3eb89557fcde60c82c08aca5941b815ef71f9ed +size 188088320 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..0eb7dec555e1b174f677a76e281930bb43f93adb --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19742146df61a2e339039c663da14629e3b3ff25fe86ef0050827a31495e684e +size 93978624 diff --git a/params_shard_210.bin b/params_shard_210.bin new file mode 100644 index 0000000000000000000000000000000000000000..d7235b2716cd507aebda00118ba3a4e7af8b080d --- /dev/null +++ b/params_shard_210.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feac5d7aeba63d71d1076cc30d24c255318d71dc82318228334173c108adb01e +size 23511040 diff --git a/params_shard_211.bin b/params_shard_211.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a7eac5b86d0d9356f281cf689fa5f10d6b70188 --- /dev/null +++ b/params_shard_211.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ab22e9a9561202c786b71610fdf47b8eefc754f331570265d7216fd799803e +size 33587200 diff --git a/params_shard_212.bin b/params_shard_212.bin new file mode 100644 index 0000000000000000000000000000000000000000..818a133a12ee26c030748d278edde480a283410d --- /dev/null +++ b/params_shard_212.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42970d6eeb36b832301d8ba03fdd383fa8434c771df7d4aca5ab7bab5a9e2958 +size 26869760 diff --git a/params_shard_213.bin b/params_shard_213.bin new file mode 100644 index 0000000000000000000000000000000000000000..1c08f21d8741a8bf1596b645ecc1d50b1f3077ef --- /dev/null +++ b/params_shard_213.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a27fff4f4d304bb2b2693e0e14411e9bc9b4ed4776aa362a766f308f964a0b0f +size 188088320 diff --git a/params_shard_214.bin b/params_shard_214.bin new file mode 100644 index 0000000000000000000000000000000000000000..9778a3c7896db755997139ee486172cefa32ab5a --- /dev/null +++ b/params_shard_214.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5bed2a3b746000ef5ba21e41df2b09f1294bbdbcc742682f034d0a5dbfa238 +size 23511040 diff --git a/params_shard_215.bin b/params_shard_215.bin new file mode 100644 index 0000000000000000000000000000000000000000..0a774629c044d0a38ad743837ea6c9306bad4dda --- /dev/null +++ b/params_shard_215.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d76d4001e4c21f4e9827132c1c69dfa2d7051195b5cf3a925b6717d9d8afed2 +size 33587200 diff --git a/params_shard_216.bin b/params_shard_216.bin new file mode 100644 index 0000000000000000000000000000000000000000..8bb1b7bd9b9fb41ab3b90784c141f37769b9d181 --- /dev/null +++ b/params_shard_216.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dbe61cd862738ea018c872a73e783a072f587ed56ab922bbce375f73b623c00 +size 26869760 diff --git a/params_shard_217.bin b/params_shard_217.bin new file mode 100644 index 0000000000000000000000000000000000000000..ee6f83d3d57d056211f2fffe3ca64a7fbe1baa28 --- /dev/null +++ b/params_shard_217.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d26cf8d14d92c29812f1634cacfb1e4a6d1950e47aa22fe272d5329bde55e79a +size 93978624 diff --git a/params_shard_218.bin b/params_shard_218.bin new file mode 100644 index 0000000000000000000000000000000000000000..259ca8ef23d650bcde7a4d1a2407a6cd091c461e --- /dev/null +++ b/params_shard_218.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ce21cb048435ec3203a26d45bce25027b60c1537393c5fe210a178e872ac01 +size 30269440 diff --git a/params_shard_219.bin b/params_shard_219.bin new file mode 100644 index 0000000000000000000000000000000000000000..694a8c6bc60134e24f60b7e5c1c8066960c12b14 --- /dev/null +++ b/params_shard_219.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:410503ca64370637d492156ef56e0e765be39070d365b9c0d3f5db7446a29be5 +size 188088320 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..130d89bb15b67f7edf220c889112e1236478384d --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc81a0b0b30d9b304b15c6e6032b69f9e412af2f2bff9a332dbadc62cd8c50d +size 93978624 diff --git a/params_shard_220.bin b/params_shard_220.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbfc750a3d7931c56c77b4882e92db754700796b --- /dev/null +++ b/params_shard_220.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4743970d459d747e512f7482d2884d47873c7a480bcbfabccf9a619e0e8630e9 +size 23511040 diff --git a/params_shard_221.bin b/params_shard_221.bin new file mode 100644 index 0000000000000000000000000000000000000000..0fb0ced19633ad70561ad4a173b4ad9857a7f056 --- /dev/null +++ b/params_shard_221.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d5c53ff13980abbb9ed9833df389acae269b9c4a61618fddafd7b15a291f72 +size 93978624 diff --git a/params_shard_222.bin b/params_shard_222.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9f1b97a0b3c758205bf0ea6e45f19f8665d26c0 --- /dev/null +++ b/params_shard_222.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4748c125c92c35c749e805ff7ee1941a59660b1380d4085babff7758abfb8923 +size 188088320 diff --git a/params_shard_223.bin b/params_shard_223.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e16ca0b3ee7c5e30e84feb674b5a7ad7f0c6c02 --- /dev/null +++ b/params_shard_223.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e3ac4133963b4ae3a76f913c67de77a206bb82bcd9d022e62f057a4847cf50 +size 23511040 diff --git a/params_shard_224.bin b/params_shard_224.bin new file mode 100644 index 0000000000000000000000000000000000000000..6bafe2ecdce06f2f947adc5aa30848882503c51d --- /dev/null +++ b/params_shard_224.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f2f2da108d401ada81b2a93dda1ea52adda5e268c7e753ec3a3122c7fb0e1c +size 33587200 diff --git a/params_shard_225.bin b/params_shard_225.bin new file mode 100644 index 0000000000000000000000000000000000000000..9bf50e697a4d47f4d222a8e056665204341cf2cd --- /dev/null +++ b/params_shard_225.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f52fac229df054e1c7f585e75dae94c0d0de9a1f143b2e7fe1f27990138ef14 +size 26869760 diff --git a/params_shard_226.bin b/params_shard_226.bin new file mode 100644 index 0000000000000000000000000000000000000000..99a24c7b1bf0224ba64807d871ffe4ad14969257 --- /dev/null +++ b/params_shard_226.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73ceb9a86a502276221f3f1e2d4d69464072e740e187f9e9772bc0f97927b8c2 +size 93978624 diff --git a/params_shard_227.bin b/params_shard_227.bin new file mode 100644 index 0000000000000000000000000000000000000000..51bef937865383d99426e172542d6327b5151c65 --- /dev/null +++ b/params_shard_227.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da303e8d087f7ce789f5cb05392bdbd3a067f0173ebd796f117ab2262cd2e0af +size 31100928 diff --git a/params_shard_228.bin b/params_shard_228.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbd75cc4e55dbb8bbbf30b3bf4ba856b53243685 --- /dev/null +++ b/params_shard_228.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4e8f86e8684c52881b02b6ad62d137a2625eebe18c871f04a32067fe86965a +size 188088320 diff --git a/params_shard_229.bin b/params_shard_229.bin new file mode 100644 index 0000000000000000000000000000000000000000..e779fd53613e7a17bf942c295645d995a7efe258 --- /dev/null +++ b/params_shard_229.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e51abaac6b6381013ee8df55b2860458194b5aad13d1beadb099a05c700bfc +size 23511040 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..b13333d4f1c18da6b3770d4f608ab725cf5d3ad2 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7529d049f11226a21d26707a424febb693d1390d03ec39335d03525cb9bb11b5 +size 188088320 diff --git a/params_shard_230.bin b/params_shard_230.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cd18f2b4c95c279937829f5d5a59a114f705ffc --- /dev/null +++ b/params_shard_230.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75bccfa248273aedf1d10453d5a4cb01f2993ffe4d1e50b209342e47f98e41de +size 33587200 diff --git a/params_shard_231.bin b/params_shard_231.bin new file mode 100644 index 0000000000000000000000000000000000000000..029e2c468145c40b516e1f602171753deaff13ea --- /dev/null +++ b/params_shard_231.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6411be6e193b67e729bd2421943481c36805dfe7b88dd3a321a3c0b7f447ec +size 26869760 diff --git a/params_shard_232.bin b/params_shard_232.bin new file mode 100644 index 0000000000000000000000000000000000000000..bfdc5389123e05b1498a2c1a7494c9fb6e991e0a --- /dev/null +++ b/params_shard_232.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c7ca1d7c985e03d1b88517572c41888723c1b142d8b3b110f1116c4769887f +size 93978624 diff --git a/params_shard_233.bin b/params_shard_233.bin new file mode 100644 index 0000000000000000000000000000000000000000..3eb9726213af00116029315cd17174fba49f9a14 --- /dev/null +++ b/params_shard_233.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c3423c187300579a2fcc1a624f908a85751e16570c039e80a041a5bcb115f0e +size 93978624 diff --git a/params_shard_234.bin b/params_shard_234.bin new file mode 100644 index 0000000000000000000000000000000000000000..6439b3a7f00842b3ab307addd3a07fa0e8de29f9 --- /dev/null +++ b/params_shard_234.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e237b9839eab70cb1184434acf2c4ac52a6eeefe6fc5316c97b3d7b3450e82d +size 31100928 diff --git a/params_shard_235.bin b/params_shard_235.bin new file mode 100644 index 0000000000000000000000000000000000000000..e664fe00d07862d204881a903b33223658515fa7 --- /dev/null +++ b/params_shard_235.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81e547e284f5fdfc122b53d1d3604f2595cd047860630b0d725e0c4eb5aa120c +size 188088320 diff --git a/params_shard_236.bin b/params_shard_236.bin new file mode 100644 index 0000000000000000000000000000000000000000..863f0ed5656d7e0167f6c08e2e3aa807dccb594b --- /dev/null +++ b/params_shard_236.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f16561c6f550c6b0269479d5b799320179ca507c5b547b520dfab74005333135 +size 23511040 diff --git a/params_shard_237.bin b/params_shard_237.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e60ff065bd059447716812f0044b67857ef6a9c --- /dev/null +++ b/params_shard_237.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5384cdd8a4b20a66b52b531cc0d3da9ec4751ffdb5dd350a2c6443673bb47ff6 +size 33587200 diff --git a/params_shard_238.bin b/params_shard_238.bin new file mode 100644 index 0000000000000000000000000000000000000000..457d27a4bc03e4e5cce79d1fd3b711a38c5805c6 --- /dev/null +++ b/params_shard_238.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dab523b8768f98d944171e24da4625a64d703523990bdc4e13fd511725bd4cc +size 26869760 diff --git a/params_shard_239.bin b/params_shard_239.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f0c93ff92ff5a3b649e02d8d4989ff0cfe338de --- /dev/null +++ b/params_shard_239.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7f969fa5f320491ab72d4bdf28d77a8bccfb38daf388c45f34baf26bb19bb4 +size 93978624 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..583fb9b1541cac0289a8632673e27479edf8638b --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa0a51ad57eaf6c429d7494534bf9612c551cbfff07dc665719274bd0abe3e4 +size 23511040 diff --git a/params_shard_240.bin b/params_shard_240.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e758b26f9f5d2df9b652abad4c95df7bb059d40 --- /dev/null +++ b/params_shard_240.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae051b2eb5ba27f0391784e858a63ff52edeeac46c4b2e128b3d155fe311270b +size 188088320 diff --git a/params_shard_241.bin b/params_shard_241.bin new file mode 100644 index 0000000000000000000000000000000000000000..b67218073c4536c17e10bdf18a2b75192061df6b --- /dev/null +++ b/params_shard_241.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278342ca529d0f9662a9d51dcede983243fd6f53a11d427d583a615affdb3e4a +size 23511040 diff --git a/params_shard_242.bin b/params_shard_242.bin new file mode 100644 index 0000000000000000000000000000000000000000..abb4487babb6404d87691b2fdf1ee3da4d37cc86 --- /dev/null +++ b/params_shard_242.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860ea7744de26cf192797479e2e75a9747ba634dd4e4b955e6e7d62f51e15c9e +size 33587200 diff --git a/params_shard_243.bin b/params_shard_243.bin new file mode 100644 index 0000000000000000000000000000000000000000..67e3bb6f37a1503c34845808abb6fea240097060 --- /dev/null +++ b/params_shard_243.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88445529f98f836b5f209081851f4b7a1d3670e64fd746ad94b9f3d5762f53b +size 31100928 diff --git a/params_shard_244.bin b/params_shard_244.bin new file mode 100644 index 0000000000000000000000000000000000000000..163162ff028e36c58307e923e403ea6cc90c4787 --- /dev/null +++ b/params_shard_244.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d574781af42e5caf9fc205d3c1eed84e457222f3e1917ce0645ddaae6565594 +size 31068160 diff --git a/params_shard_245.bin b/params_shard_245.bin new file mode 100644 index 0000000000000000000000000000000000000000..640baed0d0133afcadb7eed44981e2971de61fde --- /dev/null +++ b/params_shard_245.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91bd0657dee44fc00641987eb806380d764ce28f6a55a8e93378d58899462ae9 +size 33587200 diff --git a/params_shard_246.bin b/params_shard_246.bin new file mode 100644 index 0000000000000000000000000000000000000000..417bc3ae82e58cde9233f18aa5b59fe44983d1d0 --- /dev/null +++ b/params_shard_246.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea135c36109ca8a12248a5cebd8031db2bc663cc52555708dcdf01a5d3c1a36b +size 26869760 diff --git a/params_shard_247.bin b/params_shard_247.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9795b8325b7398a64deb4c5b8111bfed703f94c --- /dev/null +++ b/params_shard_247.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73458f8ef3588441fde52c8c39cc21c6b0a415a3cf33c440b087fc8b14a758e +size 93978624 diff --git a/params_shard_248.bin b/params_shard_248.bin new file mode 100644 index 0000000000000000000000000000000000000000..ad2e4386a8ab979fb4adb580a7405ba47a7c4c31 --- /dev/null +++ b/params_shard_248.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b9591a837276d39cd372744277ce63406d40d9ab3d84a598ddce4bd7d4006d6 +size 188088320 diff --git a/params_shard_249.bin b/params_shard_249.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed2ea1e74fa55ab77763140a4759003049143b85 --- /dev/null +++ b/params_shard_249.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd3a15af55ea54b32828714282e2148605973b96aeb1e6a811bbd547c33053a +size 23511040 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..29fb1cc7b6fb567c30bb5726164aa7d9a92a536f --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e728e855bb68c245817c4b123f28f2555a2cf3b4d423f2ab1909c3839250844 +size 33587200 diff --git a/params_shard_250.bin b/params_shard_250.bin new file mode 100644 index 0000000000000000000000000000000000000000..bca277f89442bce0e0707483be310631ce8efe1d --- /dev/null +++ b/params_shard_250.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa6f6e97eb0b0c5f3658613780c2cf24f0dea8a11bcae898e52bd473b5a9c9d0 +size 93978624 diff --git a/params_shard_251.bin b/params_shard_251.bin new file mode 100644 index 0000000000000000000000000000000000000000..281f2bbd76e008bea09e73e1dee9cfa32ad3581f --- /dev/null +++ b/params_shard_251.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1dba3661696ae52d8c201a96048a6fd015b24a2b33ffa7c3f60897c8efc160 +size 22712320 diff --git a/params_shard_252.bin b/params_shard_252.bin new file mode 100644 index 0000000000000000000000000000000000000000..404b60afdf76f8066aff2c12ebea1dafd0b761c8 --- /dev/null +++ b/params_shard_252.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc1d2b9eea4517689fa7f637506a2e2d07d10afae187c68557215c60ffa8559 +size 188088320 diff --git a/params_shard_253.bin b/params_shard_253.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf1c1ba2b5914c288d1ef40d3e8d0d11d1f6146c --- /dev/null +++ b/params_shard_253.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32efaf090f53d34f3c7fe38e645826a897757381ad7f140afe8d5f2e1ff548cf +size 23511040 diff --git a/params_shard_254.bin b/params_shard_254.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ac98618b38a09018813abfe1c1e46b8f0c67222 --- /dev/null +++ b/params_shard_254.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd658a93251138fa49e47a432975233e9a8dac077b164dc21a838ca114d8b84b +size 33587200 diff --git a/params_shard_255.bin b/params_shard_255.bin new file mode 100644 index 0000000000000000000000000000000000000000..cb51bcc15957b2bd5d1f18fd6fb79694793d9124 --- /dev/null +++ b/params_shard_255.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf92ac71ce5e957925d0ccb2ce1fe0dcadc5d566e98aae9932d6a001860fcc9 +size 26869760 diff --git a/params_shard_256.bin b/params_shard_256.bin new file mode 100644 index 0000000000000000000000000000000000000000..879d99f2f611a784bb2fbda27bfa9f66313d8359 --- /dev/null +++ b/params_shard_256.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcd6ff6827e323f05d7c05fc7ee0264eb948ad625f65b55bd993f8441006bec6 +size 93978624 diff --git a/params_shard_257.bin b/params_shard_257.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b8348edad65c8c87cf3bca8525f2b7398bdcba6 --- /dev/null +++ b/params_shard_257.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372ec350c7958519c3f04d78dad5ad792692c6b4c9825ecd316ea1281b44aab4 +size 188088320 diff --git a/params_shard_258.bin b/params_shard_258.bin new file mode 100644 index 0000000000000000000000000000000000000000..2010b1cc5b362bf2bc3b22c1c3b5a1bb16991a19 --- /dev/null +++ b/params_shard_258.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7986abe172fcc064d8c80b1cab592baff692d463d8c291999ab558d7b9a0658 +size 23511040 diff --git a/params_shard_259.bin b/params_shard_259.bin new file mode 100644 index 0000000000000000000000000000000000000000..1e6ce9cb2ac94711149e01cb2b9b9289b1996716 --- /dev/null +++ b/params_shard_259.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a07d2a14d2cf9603ea8f735d2e786706893f4fcc1deb76766c123882c6e7ad9 +size 33587200 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..7be52d0a7096c1fed0ccebcdddffea479f3c7348 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322590d85804b0ecc611c45721e1c6323e45c2daf75492d88ae9f1715dc6c1e7 +size 26869760 diff --git a/params_shard_260.bin b/params_shard_260.bin new file mode 100644 index 0000000000000000000000000000000000000000..81d7fc97da37a44aa381ffda8f23878a15b4117e --- /dev/null +++ b/params_shard_260.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e700c2b69c6ab549444f19432dcdd188e95c321947d05d2c7fc1d21b2229454 +size 31068160 diff --git a/params_shard_261.bin b/params_shard_261.bin new file mode 100644 index 0000000000000000000000000000000000000000..a32ec7020c9591b814cc5e55ee6b1beaf77137fc --- /dev/null +++ b/params_shard_261.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:913db68d99cc00b5828da012478b931f866eb33b635c211e1285c5a24f01aed7 +size 31068160 diff --git a/params_shard_262.bin b/params_shard_262.bin new file mode 100644 index 0000000000000000000000000000000000000000..60424ff909a61b7eb815ac1e261c28e9c2334662 --- /dev/null +++ b/params_shard_262.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084b52a51a52f3c0f75e43074285c30cd2298b2cf327cfd939da99d4e09730c9 +size 93978624 diff --git a/params_shard_263.bin b/params_shard_263.bin new file mode 100644 index 0000000000000000000000000000000000000000..ff54609ea6fc4bd5930e71a12f3216867868c811 --- /dev/null +++ b/params_shard_263.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b91eb3b6cc03a085b37054816ba041308b37e939b842ec40392b2a538d92454 +size 188088320 diff --git a/params_shard_264.bin b/params_shard_264.bin new file mode 100644 index 0000000000000000000000000000000000000000..46423504755e6c94cd807e02ef3d850dbdae9ca4 --- /dev/null +++ b/params_shard_264.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a8455ca924f611b06c71f8976b6434d5714e0a424505d2a7913a153fd58745 +size 23511040 diff --git a/params_shard_265.bin b/params_shard_265.bin new file mode 100644 index 0000000000000000000000000000000000000000..85532dbfe649d0b019a960947f73a7fdfbc831d4 --- /dev/null +++ b/params_shard_265.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b543cbe379d1e3c071fef164ba4713b8091ddba850e7fe9ceba510e161600cd7 +size 33587200 diff --git a/params_shard_266.bin b/params_shard_266.bin new file mode 100644 index 0000000000000000000000000000000000000000..d54deaccc45448e2faba1ca511864e12fb3a92db --- /dev/null +++ b/params_shard_266.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b23d45181ba51e64b13e48b54cee19b72ad0eecad4d6d9023624923f44324ea +size 26869760 diff --git a/params_shard_267.bin b/params_shard_267.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e70dd72fab0a516de939d68b9171bf35a81efae --- /dev/null +++ b/params_shard_267.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dccc258852c9964e2a380c565a2c91ea6b6f9c2770186fe1e6c1f64398d28a14 +size 93978624 diff --git a/params_shard_268.bin b/params_shard_268.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a33b71c725e39cf4e4e39ec3b3c9e83d1b7f2dc --- /dev/null +++ b/params_shard_268.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:583ce69da02ee985a48c32ebe06cce130eadb6b4c6a3ab41792f28e9df0d49df +size 22745088 diff --git a/params_shard_269.bin b/params_shard_269.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e4547ed36805d99662d35eb010911da452d3c23 --- /dev/null +++ b/params_shard_269.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d72e4fb7b637dcc10959d412f20851d32f70633740affca1462f45ad011d53 +size 188088320 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..207b107daf03afe729a856ae3b9379b25a8c3f86 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a94651eea9d4d696c0993744826defbf798b0c68fb2df629d3e805b084a19c +size 31117312 diff --git a/params_shard_270.bin b/params_shard_270.bin new file mode 100644 index 0000000000000000000000000000000000000000..b2ef3702c33a5c39ca52543d4df16a87a760b3de --- /dev/null +++ b/params_shard_270.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bafdf9cd6fbbfce939e544111aa898f0d13afb0459694a64d5971574ccd7a61 +size 23511040 diff --git a/params_shard_271.bin b/params_shard_271.bin new file mode 100644 index 0000000000000000000000000000000000000000..253ccb2b6a5418786595d0715ef7a951f2ea273f --- /dev/null +++ b/params_shard_271.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e1e5c9fef8a9f6243c875c6fb6e26e396d7d4613d5345549fec0e7abfb8c81b +size 33587200 diff --git a/params_shard_272.bin b/params_shard_272.bin new file mode 100644 index 0000000000000000000000000000000000000000..35156172cdd15c7e1577c0395d8c490d04acccb8 --- /dev/null +++ b/params_shard_272.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f6531fd97676aa5f119d93c552785fa2507a8be1353965ace0044ec7477870c +size 26869760 diff --git a/params_shard_273.bin b/params_shard_273.bin new file mode 100644 index 0000000000000000000000000000000000000000..6805b78b47647cebf009e99ada56fcb51aae8678 --- /dev/null +++ b/params_shard_273.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f430c673d02716bb2dbb31778637942f27bdee4fcf270ca2b8b431bfb5a03f14 +size 188088320 diff --git a/params_shard_274.bin b/params_shard_274.bin new file mode 100644 index 0000000000000000000000000000000000000000..4fa6366a0a0f88f0e9dbc1958e12df6cece7d11f --- /dev/null +++ b/params_shard_274.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e12abd01ff3cae1c0c13cd94d001dda65a1d143dcd9cdc6c0673398e72f2f9 +size 23511040 diff --git a/params_shard_275.bin b/params_shard_275.bin new file mode 100644 index 0000000000000000000000000000000000000000..16992c10ebc69b46c93eca884b28406c7ef58f3e --- /dev/null +++ b/params_shard_275.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66188674f7fa78025d06b88f23e6087a696f5500f19c2373bea21c7532da4abc +size 33587200 diff --git a/params_shard_276.bin b/params_shard_276.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d734cd979c932243c45eb48513e5eb95a91ce39 --- /dev/null +++ b/params_shard_276.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:121bcf786053ba9b3d24a33071608515bfeef1938292935dbcb483da030f9644 +size 26869760 diff --git a/params_shard_277.bin b/params_shard_277.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc1e4e8d25cf4cd6b14a170871fd0aac7b1a1016 --- /dev/null +++ b/params_shard_277.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d62356d352d1161e7114065c3f5a397257da2ea6530ac01256cd50167994b6 +size 93978624 diff --git a/params_shard_278.bin b/params_shard_278.bin new file mode 100644 index 0000000000000000000000000000000000000000..55ed81acfbdc227ede4c128b8b973229e73e39fb --- /dev/null +++ b/params_shard_278.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97f33a1ca6e66ffbb74e86495b58bf5efddca7695bdc83fb9920519013d430f +size 26894336 diff --git a/params_shard_279.bin b/params_shard_279.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ea967cfa61ac9fabcf3e4a8f5b2ee1e9e073c31 --- /dev/null +++ b/params_shard_279.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b01ece02a3e017c2840fae25a44ffe71c3f4c4c05a4969ed58103de28ca37d6f +size 93978624 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..ff0040366da3c45adcee6797282c7f9706a52485 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef85766d2d92bf2647b685861cdc47f4926bbb33f28dbfe8d13685de11dbbf8 +size 93978624 diff --git a/params_shard_280.bin b/params_shard_280.bin new file mode 100644 index 0000000000000000000000000000000000000000..55da0385b7a0e34634135bc63a0a7026d9fdae9b --- /dev/null +++ b/params_shard_280.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:223ba104973c5dcd00fdc69469e0f247d8040047bda7fed50df8c8cb16592ef9 +size 188088320 diff --git a/params_shard_281.bin b/params_shard_281.bin new file mode 100644 index 0000000000000000000000000000000000000000..320ef9c6a1032d995e7ad36a7d1293568ab96da5 --- /dev/null +++ b/params_shard_281.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa89be27ed2a6f5e12362ad15da65b34a53d87320c442f43525f1c9d5eeba1c7 +size 23511040 diff --git a/params_shard_282.bin b/params_shard_282.bin new file mode 100644 index 0000000000000000000000000000000000000000..e58bda859fb9f856a37cb9395d510251594f38c6 --- /dev/null +++ b/params_shard_282.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e166880bff54d6b5b1548f8e0c7f01dc8ddae7dbb105a81ba624d2549a64f763 +size 33587200 diff --git a/params_shard_283.bin b/params_shard_283.bin new file mode 100644 index 0000000000000000000000000000000000000000..9548c113cb69c280ae99bceb0e4fd067944ac8fe --- /dev/null +++ b/params_shard_283.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d6d033b549f8e11ae90344036179d5ee51194de00e256a231af616e92969e3 +size 26869760 diff --git a/params_shard_284.bin b/params_shard_284.bin new file mode 100644 index 0000000000000000000000000000000000000000..bbbe122001a049764aee1f0b34120c6ee62b99ea --- /dev/null +++ b/params_shard_284.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe35ffb4f847bff788e7e6b71008082168e2fc73d84264f0c8b3251f9b9568ff +size 93978624 diff --git a/params_shard_285.bin b/params_shard_285.bin new file mode 100644 index 0000000000000000000000000000000000000000..52a990a12b1891ba4a683a2fadd58f31af0263cf --- /dev/null +++ b/params_shard_285.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d858f7038a7f79bae1a7cd522b1a89bb3a712a32630bdbe5268c87e18f083d +size 31117312 diff --git a/params_shard_286.bin b/params_shard_286.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b54dd05f592fe6c746fa9dc5802ccaa6ced9ae2 --- /dev/null +++ b/params_shard_286.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea06d87a4716dc2a3528a274190b7471ff03eb49564529d5d2fab1914d7aa03 +size 188088320 diff --git a/params_shard_287.bin b/params_shard_287.bin new file mode 100644 index 0000000000000000000000000000000000000000..5aafa63856aaaa7f79f8641dc01dbd476e04ca9b --- /dev/null +++ b/params_shard_287.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9838769b68d1c368c1c75980f7cecaf25a6ef9ca60bd962554d12ea4f759ed6 +size 23511040 diff --git a/params_shard_288.bin b/params_shard_288.bin new file mode 100644 index 0000000000000000000000000000000000000000..4d6cf4c0028f0d0affaa2a93ef6b559f2fee20a4 --- /dev/null +++ b/params_shard_288.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce96a929d2e38dd8442617451c62353fb485361ef8c724f743113eadc6d6f3a +size 33587200 diff --git a/params_shard_289.bin b/params_shard_289.bin new file mode 100644 index 0000000000000000000000000000000000000000..0a07482167667895843272e72af42cb07afa9f63 --- /dev/null +++ b/params_shard_289.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e83b65465dbba37e6ba6b3edbe5f4ff757ddc152e63ce8b3ff3247bb340d50d +size 26869760 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..96f56747b044b52005350f5b873153b0b009961e --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db76e5c7e40d6572d7add37f55bd6da5563d8f8736c3c7e3279698da7fce8c86 +size 188088320 diff --git a/params_shard_290.bin b/params_shard_290.bin new file mode 100644 index 0000000000000000000000000000000000000000..90834391c37c44db2ebc04635c8d1b31727392b0 --- /dev/null +++ b/params_shard_290.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4187d82cce8e539740c6f1dedc425ee48cd01a794d23cf2d846dcc9eeb375f9b +size 33587200 diff --git a/params_shard_291.bin b/params_shard_291.bin new file mode 100644 index 0000000000000000000000000000000000000000..e5e4dfc6f4e552ea9e357843c92ab96ee07433ad --- /dev/null +++ b/params_shard_291.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05bd8f769217c50cab80d26bd766c605ace5dd4556d5ed2a4041f68e0321291 +size 26869760 diff --git a/params_shard_292.bin b/params_shard_292.bin new file mode 100644 index 0000000000000000000000000000000000000000..35b10f6311cdbfd887f53bd8cf5d45239175919e --- /dev/null +++ b/params_shard_292.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec1a4417fbf43c3058600767097ee53685f684edbe277f34a21d328a211b59c +size 93978624 diff --git a/params_shard_293.bin b/params_shard_293.bin new file mode 100644 index 0000000000000000000000000000000000000000..09230f9496f4f0a32213c773358ad5f0a185954e --- /dev/null +++ b/params_shard_293.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e709f724aa5e12ca5cdb2efbe26b2936dfe468bbac37ceb90a35f1233b9473d +size 26894336 diff --git a/params_shard_294.bin b/params_shard_294.bin new file mode 100644 index 0000000000000000000000000000000000000000..962f8452a390d443a185a8cb62372bba6ed1f700 --- /dev/null +++ b/params_shard_294.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6797fb629e0ee46212a557834c7251749633ed3b9f25b5742f718a5eb9b33a2 +size 188088320 diff --git a/params_shard_295.bin b/params_shard_295.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9ce674740ef857992fe72bae20807c9ea82f58e --- /dev/null +++ b/params_shard_295.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7a24fab0b92c476710dc1c7f6fe96ea9282695112eb4141ff3b9d899358f24 +size 23511040 diff --git a/params_shard_296.bin b/params_shard_296.bin new file mode 100644 index 0000000000000000000000000000000000000000..6be95b039cbf63c7c4d900ba3cc87a50e4658c8e --- /dev/null +++ b/params_shard_296.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fa5f4f70096e84f3d4861ee732aca00d9de4eeb598c2f384e67ecc91440ea93 +size 93978624 diff --git a/params_shard_297.bin b/params_shard_297.bin new file mode 100644 index 0000000000000000000000000000000000000000..467e524d07c9bef15a25d2bc355595363387b356 --- /dev/null +++ b/params_shard_297.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1047f07ae5a8a486fbaf8d7bae44ef378333fd4867a1f882d0f5312646604c +size 188088320 diff --git a/params_shard_298.bin b/params_shard_298.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7ff74470df35cf9fcd6145cccfcbdcda9311472 --- /dev/null +++ b/params_shard_298.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9fba62efea5759d695b46b1bfa45df793d2206dacf7c7a6d2d15d7a6c0bdf96 +size 23511040 diff --git a/params_shard_299.bin b/params_shard_299.bin new file mode 100644 index 0000000000000000000000000000000000000000..657ecee1f6dca772308989b4ee09509de389efe2 --- /dev/null +++ b/params_shard_299.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0923f64c68c1ba101445486a9af1a1a37ea921890c49c205848a3eb70adfdc07 +size 33587200 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..38b596626d113a9acf3698f4a053338bdd7775cf --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd81bc776f0c33f832a5e9ed70d2e42e0b6079481486754c798c5b1916584db +size 93978624 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..ee333ecf9fca11e0817c9830d6b8637651656349 --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc1d2351d31a1756d425f546624206446dd837f2d638597a524e304873261cd +size 23511040 diff --git a/params_shard_300.bin b/params_shard_300.bin new file mode 100644 index 0000000000000000000000000000000000000000..46adea2933853a8b082407d18c20ca6d4d475184 --- /dev/null +++ b/params_shard_300.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f9fe0b7c4158ea56ef8c40e4129ab6fdfb3e7d51c43351e2488628686cf6f8 +size 26869760 diff --git a/params_shard_301.bin b/params_shard_301.bin new file mode 100644 index 0000000000000000000000000000000000000000..578ea86ef8e442939eb0f249d458ef46f3b097e2 --- /dev/null +++ b/params_shard_301.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00ae32c893e33d33cc001aa7a1dc7b3a6ee9ceabb1d75ac5f19ec44c24e79882 +size 93978624 diff --git a/params_shard_302.bin b/params_shard_302.bin new file mode 100644 index 0000000000000000000000000000000000000000..7bfd6a4d3e371d6ea588c00b921f5f35ddb62411 --- /dev/null +++ b/params_shard_302.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ebd811017caedc626f30a2ead452a06a437f9ebcbc4e642a3f37f06c70bbae +size 31100928 diff --git a/params_shard_303.bin b/params_shard_303.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f2f5f031c1819f96a2e364e2be6372746119d17 --- /dev/null +++ b/params_shard_303.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:887ccf3b8934c5489114bab1c9144353295d5be696b21da8161caf2db1d13b3a +size 188088320 diff --git a/params_shard_304.bin b/params_shard_304.bin new file mode 100644 index 0000000000000000000000000000000000000000..c94faf8c304d5e567cd452cc86731f01ed0224a6 --- /dev/null +++ b/params_shard_304.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e12d98f0306e516b70006acc4d9e88a570b7dbbe493f38b38ba4052a544e911 +size 23511040 diff --git a/params_shard_305.bin b/params_shard_305.bin new file mode 100644 index 0000000000000000000000000000000000000000..79f928bfe0ee7d7706ef6de9da6c4bcf3066ad8d --- /dev/null +++ b/params_shard_305.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b29199747dc39ea1688f798a4c8cc400902c40e87e558e4d788ccdf26e0074 +size 33587200 diff --git a/params_shard_306.bin b/params_shard_306.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e2afa846c46a8e16be146aa602f4ce571f4ba5d --- /dev/null +++ b/params_shard_306.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:778dcd70c26f4bd3f22508027a60620d3bec3baf55e8c4249cd4ca8dd351c81d +size 26869760 diff --git a/params_shard_307.bin b/params_shard_307.bin new file mode 100644 index 0000000000000000000000000000000000000000..9e64a1a585682ebc53cf71966e6e209d58bcf505 --- /dev/null +++ b/params_shard_307.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0540b2a52db01af7d38b7f868237d378828d4b65519521520169b3d9ef8361f8 +size 93978624 diff --git a/params_shard_308.bin b/params_shard_308.bin new file mode 100644 index 0000000000000000000000000000000000000000..3adbfc15ae832978ea105287595087b67e1c8a4c --- /dev/null +++ b/params_shard_308.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5abb9615c38986b42092f5f16effa7f1c60bc2e6f2d7886de40653b8b1b88c2 +size 188088320 diff --git a/params_shard_309.bin b/params_shard_309.bin new file mode 100644 index 0000000000000000000000000000000000000000..c0bf606c6b4588bf250b549e26a132601afd28b6 --- /dev/null +++ b/params_shard_309.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053308cc6748062db6f13f07551905b5f857547c16e282538070b76d3e614d31 +size 23511040 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b39835530abe14743725a3ded2a430aec8a47b5 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a54fa6bf7d9969436c914b36424efad98c814ede895dc3e068070b775da3472 +size 33587200 diff --git a/params_shard_310.bin b/params_shard_310.bin new file mode 100644 index 0000000000000000000000000000000000000000..a9bc092b7dedc59523e7ccb3d6dd8d9e27d34eed --- /dev/null +++ b/params_shard_310.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee748714e36b53c0766537b14e563e64ab428c80064064955ce644a3664ee46 +size 33587200 diff --git a/params_shard_311.bin b/params_shard_311.bin new file mode 100644 index 0000000000000000000000000000000000000000..42634ec7528ca90232383ebb0cebee9e2b12ddcc --- /dev/null +++ b/params_shard_311.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73106967dddfa08c6e4a817a0e43b70d3eaa8690e020b510e43f8bd3ea6429df +size 31117312 diff --git a/params_shard_312.bin b/params_shard_312.bin new file mode 100644 index 0000000000000000000000000000000000000000..594c09190b65871d136a61c59891185f76057219 --- /dev/null +++ b/params_shard_312.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31697651da9910fce94858625b3d599cdbbe3b4baff3dde7f67e07358b084318 +size 31068160 diff --git a/params_shard_313.bin b/params_shard_313.bin new file mode 100644 index 0000000000000000000000000000000000000000..df8417805937adca105742e46f1439d0ae153e94 --- /dev/null +++ b/params_shard_313.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7d6a6d34bc4b00649d6a40f40030af6735194c1dc8a503d2e3daabf4336212 +size 93978624 diff --git a/params_shard_314.bin b/params_shard_314.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c55d34925a221fd9daec10b69c54186bb636f1b --- /dev/null +++ b/params_shard_314.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69706906e8077e453fc598240a149544e5d788739d579ac60c5da6c5597da806 +size 188088320 diff --git a/params_shard_315.bin b/params_shard_315.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b70288d35162dcdab09c4c3133d7a0db1616593 --- /dev/null +++ b/params_shard_315.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefc2408ae4cfbcae6a2538ba5683fb43bd3ff87eb23f50dd8ac2c174bd720d7 +size 23511040 diff --git a/params_shard_316.bin b/params_shard_316.bin new file mode 100644 index 0000000000000000000000000000000000000000..309dc890f678d2fb01798e3752451e6c705b5940 --- /dev/null +++ b/params_shard_316.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bd6ace990a4222223d73d70c6cc17e9844518cdf4bf0e1fe86547250d5f2d5 +size 33587200 diff --git a/params_shard_317.bin b/params_shard_317.bin new file mode 100644 index 0000000000000000000000000000000000000000..48fc7dd110f6434e2089c52590dfe558d845aa82 --- /dev/null +++ b/params_shard_317.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c25f410aff4ff2639657a16c36e1dace5ac4eb9f3a02dd663e2408acb45090f0 +size 26869760 diff --git a/params_shard_318.bin b/params_shard_318.bin new file mode 100644 index 0000000000000000000000000000000000000000..e1a9b9f5e442632fc7c26f3affe1c1965352fea8 --- /dev/null +++ b/params_shard_318.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da77c7832d0c5ad47e8b15a86e9faf295e005e429ce10bb4aa6ca579c451355 +size 188088320 diff --git a/params_shard_319.bin b/params_shard_319.bin new file mode 100644 index 0000000000000000000000000000000000000000..adb6db00cac87c43f5ec8fffb55a0951e1678f8f --- /dev/null +++ b/params_shard_319.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9e006b46a1af7e07f2c263f78503a1fd51052ba102dfd7b763b6d6ced22e813 +size 23511040 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..b680b362bb52bf6b557ab6d6eedfd39a2637d360 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e0b77886c9285a3e94f9a4f79cc495e281642ab0cba5ab8649ac2eb168c24bc +size 26869760 diff --git a/params_shard_320.bin b/params_shard_320.bin new file mode 100644 index 0000000000000000000000000000000000000000..d167774e323f81b523f2909b6329e9daacc3cb89 --- /dev/null +++ b/params_shard_320.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b11ce496956e7b0f5c5c4b44b7c144f196886ca9fb462792177b6e3f98ea56 +size 33587200 diff --git a/params_shard_321.bin b/params_shard_321.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ba3e40a1314a71ed53ca9aff8642fa731aa66b1 --- /dev/null +++ b/params_shard_321.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce08d49161bd7eb3ccf0a45fb3d975c8b9e7a0db73651b689d18bf9c9cba8f6 +size 26869760 diff --git a/params_shard_322.bin b/params_shard_322.bin new file mode 100644 index 0000000000000000000000000000000000000000..b2c22f4f556651809202513e04859e088f31b50d --- /dev/null +++ b/params_shard_322.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448e4ad44d66b2601e2464029ad892c0b4e9edd8980b827f201cd121c0e42e6b +size 93978624 diff --git a/params_shard_323.bin b/params_shard_323.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c7d04dceb697949807d59196676068621e3b5da --- /dev/null +++ b/params_shard_323.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633067a60f960aff2233d41574609bc9334e04642e08a2c1a2377ccfe28296f5 +size 30269440 diff --git a/params_shard_324.bin b/params_shard_324.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb7e97a51deb97c68e3a2ffe9d57091c2813bbe9 --- /dev/null +++ b/params_shard_324.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26bf3745c129650a2ad2dbaa4b9d79412d6fa79ce930799a5f72763770279019 +size 93978624 diff --git a/params_shard_325.bin b/params_shard_325.bin new file mode 100644 index 0000000000000000000000000000000000000000..24ba855b305db7be795571a75fedb5369eef3cb7 --- /dev/null +++ b/params_shard_325.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05db6075553bd2d5962daaa341b3b2db7c316e6b0f6aab28591b188119ab72af +size 188088320 diff --git a/params_shard_326.bin b/params_shard_326.bin new file mode 100644 index 0000000000000000000000000000000000000000..d11603a7e5e00c18ed21db176cd18d01e8071a59 --- /dev/null +++ b/params_shard_326.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9507b953db042cdb413af9b76c9f1cdcb8c58cfe171b2e081d9fc80597725459 +size 23511040 diff --git a/params_shard_327.bin b/params_shard_327.bin new file mode 100644 index 0000000000000000000000000000000000000000..47a3861b3c14373500f262a9734df8d65ba35de4 --- /dev/null +++ b/params_shard_327.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8365a2b463f4aafef177f0d8fb7cf0dba088e21517ca10feb3427fe4c19094b3 +size 33587200 diff --git a/params_shard_328.bin b/params_shard_328.bin new file mode 100644 index 0000000000000000000000000000000000000000..05bc3690d8f9fa9597d5edecc8a6dc23bc0d40ae --- /dev/null +++ b/params_shard_328.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6084b042ead0f7d5fb61c6337dddd06bbb23d7f9031bd8bd22ff1b2a1570aecf +size 26869760 diff --git a/params_shard_329.bin b/params_shard_329.bin new file mode 100644 index 0000000000000000000000000000000000000000..17ba3400e0310e3501f96d13228b140388019465 --- /dev/null +++ b/params_shard_329.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3145448b224dbf58b4076366f6e25153ee8820849fa02806350b39f10402503 +size 93978624 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..397b1434d504b34888ad8ab507cb5d298b21393c --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba976fbd3b98cdde85188e0e527869c5bb164da445390a9a7c5a5ca0e01a207 +size 33587200 diff --git a/params_shard_330.bin b/params_shard_330.bin new file mode 100644 index 0000000000000000000000000000000000000000..91900b8b5651bd3707bb16e6d079269d516eb365 --- /dev/null +++ b/params_shard_330.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1fcaccc1ba744dd44b5b58c6b73b2b78913b415227b9cc074354681336b39ef +size 31117312 diff --git a/params_shard_331.bin b/params_shard_331.bin new file mode 100644 index 0000000000000000000000000000000000000000..cda67bcd1d180bb9b081b74711d56be04b87ebd6 --- /dev/null +++ b/params_shard_331.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362eba3c0120a180963b79353181e5b28ac1fddcb25e13610b9a6d6fc42351f4 +size 188088320 diff --git a/params_shard_332.bin b/params_shard_332.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4f518aa18a3d5243d8e455076bc86d63de93674 --- /dev/null +++ b/params_shard_332.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b77e8bd4cb1da7300196d269d74d0df49179bbc0e843b048761f5148d65b95 +size 23511040 diff --git a/params_shard_333.bin b/params_shard_333.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf7145f2ef415c6fcebda2c1ed8e3d210b9e22b0 --- /dev/null +++ b/params_shard_333.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fd26127f86926a9be838b8c8f5a122961a039934fcea73c181ee2f5e8222a2 +size 33587200 diff --git a/params_shard_334.bin b/params_shard_334.bin new file mode 100644 index 0000000000000000000000000000000000000000..e4cc68f3d4bd206a55d8968c2068c2baf557b319 --- /dev/null +++ b/params_shard_334.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1bfb68b53ec0840ebb5ad5b06831c33bc899ee263e3ef2eb8ac9a083b65190 +size 26869760 diff --git a/params_shard_335.bin b/params_shard_335.bin new file mode 100644 index 0000000000000000000000000000000000000000..8548371093285043a65a5fdccf0aaba40c085bad --- /dev/null +++ b/params_shard_335.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d36796b321d82194c315be949d6bf0cadf9ac14a0b497071375c9ba09adc27 +size 33587200 diff --git a/params_shard_336.bin b/params_shard_336.bin new file mode 100644 index 0000000000000000000000000000000000000000..2feed1e08b0f4717e05f0f7e0a006471b9441d24 --- /dev/null +++ b/params_shard_336.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7408c36ec98025f25b3adaa6fdc471e26202c883b5a73d1fd4444ff30224bf3f +size 26869760 diff --git a/params_shard_337.bin b/params_shard_337.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa2d32817b0ca7d6e4b1dbf4cd449a2b25a168c5 --- /dev/null +++ b/params_shard_337.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8098ee55d5432af02580d6145887fe08f879058ae438533fc1ae40bd137b9f8 +size 93978624 diff --git a/params_shard_338.bin b/params_shard_338.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d7574ddd3b945ca5f3563d33cd5433e453ee9b3 --- /dev/null +++ b/params_shard_338.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c84bf468883ee7baa7894d8d1aebd62dbb3cc3929019c8cbf4d28fdcc86fe9 +size 26927104 diff --git a/params_shard_339.bin b/params_shard_339.bin new file mode 100644 index 0000000000000000000000000000000000000000..4ab9ae63434ee1df0082fa798a8c39e2e7e1e9c4 --- /dev/null +++ b/params_shard_339.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c723fb6c124d147bffb699e573cbf76a9548fff5c7bf0b739d707059c108306 +size 188088320 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..de74d50b0c4c59dd32ff71d90e590fac44d8dc36 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9ca0602f98e368d25d6a07f1bd2076ae8f4d6741995cc0a0bd938234faab784 +size 26869760 diff --git a/params_shard_340.bin b/params_shard_340.bin new file mode 100644 index 0000000000000000000000000000000000000000..dfe19b552b3063a8cfc90ae0ee7e6d7079c65a75 --- /dev/null +++ b/params_shard_340.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b74d4286851091d13b855c1b9edcadf66d01d3f80d6e1bd9cacd8af5457a2a52 +size 23511040 diff --git a/params_shard_341.bin b/params_shard_341.bin new file mode 100644 index 0000000000000000000000000000000000000000..3c44f4a3983a153014c4f40eba51e4a762a4c17a --- /dev/null +++ b/params_shard_341.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4841b9939e162988319fd0dad315ae0733945f927150fcc77089eba4367806c +size 33587200 diff --git a/params_shard_342.bin b/params_shard_342.bin new file mode 100644 index 0000000000000000000000000000000000000000..a3c086556948f478b2fa65d65d8b1c754c28a9b3 --- /dev/null +++ b/params_shard_342.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61fae8ef9bf0095430bcc8d05b0cf4ed25bb389e504bacdb7200c6315f264eaf +size 26869760 diff --git a/params_shard_343.bin b/params_shard_343.bin new file mode 100644 index 0000000000000000000000000000000000000000..a57f1030755fc64cdbfde6d9de267edd97659426 --- /dev/null +++ b/params_shard_343.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde837f9cb85f3e1d73beb01fe9e6302150f0a7e7033d46982970f7849de153c +size 93978624 diff --git a/params_shard_344.bin b/params_shard_344.bin new file mode 100644 index 0000000000000000000000000000000000000000..35ba56e40b5e077351a85535573e462e7db5b433 --- /dev/null +++ b/params_shard_344.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df990503d192d4a7889b13485ab1308726b038fe514ac01dd847814480b3f580 +size 188088320 diff --git a/params_shard_345.bin b/params_shard_345.bin new file mode 100644 index 0000000000000000000000000000000000000000..862eb4b8b9e3656923769568a835d8510a478e71 --- /dev/null +++ b/params_shard_345.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42bb96059a8a301ce25ee776ebf29b2b86143fae0e2ca01fd6fa89376eef434f +size 23511040 diff --git a/params_shard_346.bin b/params_shard_346.bin new file mode 100644 index 0000000000000000000000000000000000000000..a7809dea9027b15f4292886d9ec72f2fe9a524a1 --- /dev/null +++ b/params_shard_346.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7c07597663a942368e5551bca137909b22f09a888813706c85a01df64b942e +size 33587200 diff --git a/params_shard_347.bin b/params_shard_347.bin new file mode 100644 index 0000000000000000000000000000000000000000..14ccd28d0709d35ab6b444ce635f6f7b6dc250d3 --- /dev/null +++ b/params_shard_347.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8fb0ffa060aed4486aa7ed0c0e1f3ebfe992923a22f237c563f03d47ab011d9 +size 31100928 diff --git a/params_shard_348.bin b/params_shard_348.bin new file mode 100644 index 0000000000000000000000000000000000000000..12c7d7db01fcc86e97d3f72e8ef4279fad8484ab --- /dev/null +++ b/params_shard_348.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b850eb3f7733ebb79813c20e3920ebce43de72a3f2c45cc711d862e3379ff89 +size 31068160 diff --git a/params_shard_349.bin b/params_shard_349.bin new file mode 100644 index 0000000000000000000000000000000000000000..879dc6ac2e21f4e1ec74c8b8e5def7bf4ebee47b --- /dev/null +++ b/params_shard_349.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2db095595b3ae5e562b966c3b7d6a5e0a17cb537cc053bfabc317ae3adefa6 +size 33587200 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f86d926cdf5b8b332adc24c5b7a4598e83c3a35 --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde783dfeea6954d07dc918bd07d271ba4a35bcd0dc4386c67fa3426d16a3607 +size 93978624 diff --git a/params_shard_350.bin b/params_shard_350.bin new file mode 100644 index 0000000000000000000000000000000000000000..036adad8f7faf66c7e4503b0a92ffd789118b8e1 --- /dev/null +++ b/params_shard_350.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25aeac443fc3aabb935de28ff5c0264d8ea9f6fb5244bc2e7d608b6e076ff734 +size 26869760 diff --git a/params_shard_351.bin b/params_shard_351.bin new file mode 100644 index 0000000000000000000000000000000000000000..cb6473c8961a84e7aa5d63e66de47b828c5127a3 --- /dev/null +++ b/params_shard_351.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c45cd52d7f9b28d8410bd98766d8392cab47a6e3f6de686f83926b6e46b21728 +size 93978624 diff --git a/params_shard_352.bin b/params_shard_352.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3c611022a487e0d744a9dfc30b78c4cc0c5a163 --- /dev/null +++ b/params_shard_352.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac65c145e25b759a7c49a5768d91b85da2c589c8ebc8afa194767bafc5acf48 +size 188088320 diff --git a/params_shard_353.bin b/params_shard_353.bin new file mode 100644 index 0000000000000000000000000000000000000000..9910c06c08896fb06a9e2886532cbec19aefafe4 --- /dev/null +++ b/params_shard_353.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db986012e3b2f211f28a9c27de670c270ed958b577ec2aa7a78d23589de78fdc +size 23511040 diff --git a/params_shard_354.bin b/params_shard_354.bin new file mode 100644 index 0000000000000000000000000000000000000000..abb890682d44b4215d9d5daf77a998069f955137 --- /dev/null +++ b/params_shard_354.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8656ed29e384aad3d148b320f80929a8ffdc9a119424400db4dd48be07b99c85 +size 93978624 diff --git a/params_shard_355.bin b/params_shard_355.bin new file mode 100644 index 0000000000000000000000000000000000000000..6131185b879771c5c23a4ac61723e18b3459fb4d --- /dev/null +++ b/params_shard_355.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43411a93133f1e546b32e9b0eb53109db69819b4b2455251ce87caec22add57d +size 22712320 diff --git a/params_shard_356.bin b/params_shard_356.bin new file mode 100644 index 0000000000000000000000000000000000000000..7b0cf9946d4c5d0c4628471e4e1f0da3f8945180 --- /dev/null +++ b/params_shard_356.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6a37e39e674b5a7b542f3734865c34eda9598be3bb2c8025d4ada42b6c23c2 +size 188088320 diff --git a/params_shard_357.bin b/params_shard_357.bin new file mode 100644 index 0000000000000000000000000000000000000000..113627c945d047068533d8f43b199ebc53c4691e --- /dev/null +++ b/params_shard_357.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c0a179193b5be847501c8926c07ead34c8002cee41351b179ea43fd57312638 +size 23511040 diff --git a/params_shard_358.bin b/params_shard_358.bin new file mode 100644 index 0000000000000000000000000000000000000000..b6ad2f0a5577c7fe488ea7da59a3c1990d8c63cf --- /dev/null +++ b/params_shard_358.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab5d7941126b75f0dd37d8cfe71b2a45f843851db360a14a06e457b80076322 +size 33587200 diff --git a/params_shard_359.bin b/params_shard_359.bin new file mode 100644 index 0000000000000000000000000000000000000000..f6009d1cc7fa50a50bb2fa4fad6204104378436b --- /dev/null +++ b/params_shard_359.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:334a910f6fc81159e97314601401d70da81d029ce5dbacf707b40287870ef8d7 +size 26869760 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..302df781f622ff7fa26b2e49c71bb249b26f6a71 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf6d944a9ec379d26716ac42bd291b859b498fe8b53a88fcdc197b27980bc7b +size 30269440 diff --git a/params_shard_360.bin b/params_shard_360.bin new file mode 100644 index 0000000000000000000000000000000000000000..a58805b50358d91ce9eb624a967b730767d83b0b --- /dev/null +++ b/params_shard_360.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ed0e80a39123c6b4e661f7001a8eb312f5c3df4f6646a998115479121df079c +size 93978624 diff --git a/params_shard_361.bin b/params_shard_361.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab7c48ecfc011ac3bec8e2c498f2592a932634d2 --- /dev/null +++ b/params_shard_361.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67273879a9178598d39a23e463456da4cc91c682d247d0224812cbd5c2d004ed +size 188088320 diff --git a/params_shard_362.bin b/params_shard_362.bin new file mode 100644 index 0000000000000000000000000000000000000000..87cde9f6d178a8e5a081958a1c7912132e94d9ab --- /dev/null +++ b/params_shard_362.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3e0f6e1d04c83f911fb9f0a9c65e8acff52f7545a2f0d742c8a7c8bca676b1 +size 23511040 diff --git a/params_shard_363.bin b/params_shard_363.bin new file mode 100644 index 0000000000000000000000000000000000000000..ba70103da4f67687b14ccc4d2918f5026b76cfec --- /dev/null +++ b/params_shard_363.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872f61da39b6c09ded3f78f8d62fe1791107d0c0c0cc3d689e3daee36ad23348 +size 33587200 diff --git a/params_shard_364.bin b/params_shard_364.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b2514fe5844ffe8187a7c43165f21369283c0b2 --- /dev/null +++ b/params_shard_364.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d6be4da46c8529b36ca03a31d39f6101821b7ebe1fd565909f6f2078d59822 +size 31068160 diff --git a/params_shard_365.bin b/params_shard_365.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a1ba6f617815f1f2844cf35a8e9578c76e71118 --- /dev/null +++ b/params_shard_365.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816762e6d424edea6a350f0ae2fe256684017273527c6c932ca3b0b08006955c +size 31068160 diff --git a/params_shard_366.bin b/params_shard_366.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1238c98636b94001a6ac5bbb679cdbab4a13871 --- /dev/null +++ b/params_shard_366.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9334ac1f0b7fa2ea753bbd65435fb2b657edb8c0c8c4f8fbf54410b019837575 +size 93978624 diff --git a/params_shard_367.bin b/params_shard_367.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f17a72c08040572c009a4db30d20ead01879f6c --- /dev/null +++ b/params_shard_367.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006e47133eaf5fe463f4d8cbc30b7959c2a762e6284773b51fe8e86b71a6cb9b +size 188088320 diff --git a/params_shard_368.bin b/params_shard_368.bin new file mode 100644 index 0000000000000000000000000000000000000000..98c806081cba5a00a20b8438ad750e87336eb72e --- /dev/null +++ b/params_shard_368.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca90184ee0d2f3c48a9c940a7b4daba966ea54436f7d6443c203e9e5370926a8 +size 23511040 diff --git a/params_shard_369.bin b/params_shard_369.bin new file mode 100644 index 0000000000000000000000000000000000000000..4a078b8d24d929c54fec139b054a224bb87d11f4 --- /dev/null +++ b/params_shard_369.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a0f8115082170eabb4893f2acf835636a162994381ef9529ee5c5df454f02f6 +size 33587200 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..37c2ea481128f9a42cc4d6c65e94a0259a3843a9 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9cbcf2a9959e1a72a5f49860290128cf2ad0b21b279d633609fc40498a7253 +size 188088320 diff --git a/params_shard_370.bin b/params_shard_370.bin new file mode 100644 index 0000000000000000000000000000000000000000..27eae7139b55c242bfa8c3854a5602406c69c011 --- /dev/null +++ b/params_shard_370.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84543551a451c72522a781e4446f9418065a7a536d7834132963d6352edeea2f +size 26869760 diff --git a/params_shard_371.bin b/params_shard_371.bin new file mode 100644 index 0000000000000000000000000000000000000000..c1eb102bab2167432642b49d3fa15f52c57265ad --- /dev/null +++ b/params_shard_371.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9edaba567b1599da0f411acb5cf4005b7a29af92764f9c6ae16de648ca543a +size 93978624 diff --git a/params_shard_372.bin b/params_shard_372.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf6a2651f4d784281da7c469cd689fdfeddbb631 --- /dev/null +++ b/params_shard_372.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee1f7263f65c28038d3cc4ff99061423d6dc5c000f9531aebcab45acbe3ad212 +size 22745088 diff --git a/params_shard_373.bin b/params_shard_373.bin new file mode 100644 index 0000000000000000000000000000000000000000..cae76872916eb5729b025d1b658a4b1ca9ecce4f --- /dev/null +++ b/params_shard_373.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b11abbd78891b582377fd64c492e5f6d4de3eb75f91dd1b09897f09b8204f82 +size 188088320 diff --git a/params_shard_374.bin b/params_shard_374.bin new file mode 100644 index 0000000000000000000000000000000000000000..55db40199b72f7611e3d4e55bef79e3e1b454eb9 --- /dev/null +++ b/params_shard_374.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1c3b28f54eac4a68d8ee2933b0da88ab818603e10aae97ffe765eafb59ba4d +size 23511040 diff --git a/params_shard_375.bin b/params_shard_375.bin new file mode 100644 index 0000000000000000000000000000000000000000..5bf1f16c73e3dfa64a72a9367c5cedafccd64444 --- /dev/null +++ b/params_shard_375.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd49144512cbfe2909433fe057f8c7a58d5b1fb7066a9b2c932234d4e8bde97 +size 33587200 diff --git a/params_shard_376.bin b/params_shard_376.bin new file mode 100644 index 0000000000000000000000000000000000000000..000061200621fb299039be22680d85a457ace89c --- /dev/null +++ b/params_shard_376.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d505991f64b9f4931c859fdda909178fd6e782ede2dcbf9c1344299e907d25 +size 26869760 diff --git a/params_shard_377.bin b/params_shard_377.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f54960aeb53531ef3ce3eb8a33179204055e38d --- /dev/null +++ b/params_shard_377.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17f3953199cc31f4261fa91f1cdd2d5267522f8d0c490e012e6c5d9a55b065b8 +size 188088320 diff --git a/params_shard_378.bin b/params_shard_378.bin new file mode 100644 index 0000000000000000000000000000000000000000..45ac4869f48958f353d4bea8d9575fff30e1a141 --- /dev/null +++ b/params_shard_378.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f001219c8516542f51c68bd02e1f7a53d19537981be601d213a8381bd86e71 +size 23511040 diff --git a/params_shard_379.bin b/params_shard_379.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8914a7ecb6d6f0684a9377fb752743c581ff2ef --- /dev/null +++ b/params_shard_379.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3194bdaf2ce7989673940d5a5ddf1a7503e1b6c01eea95d37678fed9dca4ce58 +size 33587200 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..2618681bd39ecdd22857b3bc44f9c85814c4183e --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da4be21ca402f04220807492acca81cbea761338915541426ac293f8b47e589 +size 23511040 diff --git a/params_shard_380.bin b/params_shard_380.bin new file mode 100644 index 0000000000000000000000000000000000000000..b25f02c1c99472b06689b60ac2ce7d9e150c6289 --- /dev/null +++ b/params_shard_380.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428a4deabe1cc2aa6c1ef5af0bc9e72f8f6c1cb83c72dc1ae783757fe20b22f5 +size 26869760 diff --git a/params_shard_381.bin b/params_shard_381.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e38ce67c1575ee381974ffa7c41035ceb6ecba6 --- /dev/null +++ b/params_shard_381.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5701f1afc97c03f297436c82cd64214893017380bdb11a09a34d5e8eb67a6b8 +size 93978624 diff --git a/params_shard_382.bin b/params_shard_382.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7cdf393c1f11138c1deeed5a0488b47dc5091d6 --- /dev/null +++ b/params_shard_382.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa39a6d80840ee6e7d1505c5358d9030bde34100eb2af356136f091e36a5308 +size 26894336 diff --git a/params_shard_383.bin b/params_shard_383.bin new file mode 100644 index 0000000000000000000000000000000000000000..f7f4b73c0249ad41645cee3a130ffaafe21b37ad --- /dev/null +++ b/params_shard_383.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5334cf388e620ea7141cf00a7b78d077129167b4b8fdf0ff25c3eda43b3dc4f7 +size 93978624 diff --git a/params_shard_384.bin b/params_shard_384.bin new file mode 100644 index 0000000000000000000000000000000000000000..04142527a1f37309d0b6a34cc354005b56fc2723 --- /dev/null +++ b/params_shard_384.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c79e835e6a81e0b0f326060c1f9676390462f5f1e71e335c6cff53fec9c083 +size 188088320 diff --git a/params_shard_385.bin b/params_shard_385.bin new file mode 100644 index 0000000000000000000000000000000000000000..8976abbb0309de4439c0d5c03c1bf7add5cb8fa0 --- /dev/null +++ b/params_shard_385.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:909c7ac19d1165070dd6c4f1ebe2b28b493304ae0ac05ed51b51b06a67c893b6 +size 23511040 diff --git a/params_shard_386.bin b/params_shard_386.bin new file mode 100644 index 0000000000000000000000000000000000000000..48334334df8dba191afdbbcfbb70f976e341bb8b --- /dev/null +++ b/params_shard_386.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:167a825916fb1568530f0ec3e0347439830dae572c136c8b1aa7d4f4533772ad +size 33587200 diff --git a/params_shard_387.bin b/params_shard_387.bin new file mode 100644 index 0000000000000000000000000000000000000000..24843286fe35a2925b8e114cf16b1fd3db4ec0a3 --- /dev/null +++ b/params_shard_387.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370f8e702cfb3063ed8e291d0bed8ab8d381e565921ee09dee911251eeb7850a +size 26869760 diff --git a/params_shard_388.bin b/params_shard_388.bin new file mode 100644 index 0000000000000000000000000000000000000000..aeebbf07bfb652805e11bbfbe2f09e8e86d09400 --- /dev/null +++ b/params_shard_388.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c6d11a6d05016e42182d2ab533b5df1ded91b559b97f007e449a0bd2eb4d92 +size 93978624 diff --git a/params_shard_389.bin b/params_shard_389.bin new file mode 100644 index 0000000000000000000000000000000000000000..ebac7a82693e5d175f4dda616384d17fe0d348c2 --- /dev/null +++ b/params_shard_389.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be84e186444c865fe813bea4610c0c949f31e8c37ef328f2091c53722f63b1ea +size 31117312 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..24ca21f72f6acf979f20cf81a424ac947e7a9099 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77b67cfae68b24eba7d27792eab49374c7e386c742aaf214fdd8f351424d3e00 +size 33587200 diff --git a/params_shard_390.bin b/params_shard_390.bin new file mode 100644 index 0000000000000000000000000000000000000000..0fde75c56c03828935d5136dc876705ee62c5687 --- /dev/null +++ b/params_shard_390.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d5d1ffbed96a008fa554c6cf8123995e23deb934610f0b29489863c18427c6 +size 188088320 diff --git a/params_shard_391.bin b/params_shard_391.bin new file mode 100644 index 0000000000000000000000000000000000000000..b9d7770b516b0944813e98955a51b2aed6e27b19 --- /dev/null +++ b/params_shard_391.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d1c9da755a463e27a903c7ecb4ae7894191184846262567ecaf03ace686f2b +size 23511040 diff --git a/params_shard_392.bin b/params_shard_392.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0707821a35436a8cf8fe6c7cda83deab010bb58 --- /dev/null +++ b/params_shard_392.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16badf07cb67327742cb06599df31d81e13fa35b097df31b1f579d38ea33279a +size 33587200 diff --git a/params_shard_393.bin b/params_shard_393.bin new file mode 100644 index 0000000000000000000000000000000000000000..6d8acc5f1b022785ade59473df14654206d93e14 --- /dev/null +++ b/params_shard_393.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b79cfda3e4b8dbb60eff5ff0a0ba95dace0702382936121a13f43fc729b8e6 +size 26869760 diff --git a/params_shard_394.bin b/params_shard_394.bin new file mode 100644 index 0000000000000000000000000000000000000000..e340d857b0ea51590db99f7b69e1cf0234a12c18 --- /dev/null +++ b/params_shard_394.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85350c3211c08746d6de8c41872f2f286c9e66eb50f7222de51c368e402ae743 +size 33587200 diff --git a/params_shard_395.bin b/params_shard_395.bin new file mode 100644 index 0000000000000000000000000000000000000000..e28d926fc1fd31beb7e9dea24eca797944f0af56 --- /dev/null +++ b/params_shard_395.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c2e30b94a24473a5fe914e95f0d752dd23fb8d2d014cb9ef78c7cb548936b8 +size 26869760 diff --git a/params_shard_396.bin b/params_shard_396.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6dea5d8946f39a7a7beca84ea9911dbd7947f2c --- /dev/null +++ b/params_shard_396.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb93a3dd66b9ec3b1ab7a71b4171232dbbe94b493bac230d7188d72693c2cba +size 93978624 diff --git a/params_shard_397.bin b/params_shard_397.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a589503ff4683f83a6593467de01bc603f64efa --- /dev/null +++ b/params_shard_397.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0c27a60ce38e509c8a7adb92a9e47f3306285e75e1a8fa1d4eab879631ceef +size 26894336 diff --git a/params_shard_398.bin b/params_shard_398.bin new file mode 100644 index 0000000000000000000000000000000000000000..eabb9b22a9fe35dff66054eb47be6e7b141dd07a --- /dev/null +++ b/params_shard_398.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198e53d03cadfad2bc46c5c5d8ba647e1e7b69ab480754a6aed29a688a5ca24b +size 188088320 diff --git a/params_shard_399.bin b/params_shard_399.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e1584bf72f5f0068664e347cbed045e5d89bb3f --- /dev/null +++ b/params_shard_399.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce1e7804995d75a5fddfec32b1f414ef0ff645a839a03e2020b50ac5c689b8b5 +size 23511040 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..51a4a2795d2efd6801e40f3e77cc956cd032ff35 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2302367b027921c7b535a4d2ae29739a058315e8e578fa52f9a6bb7c7b6aae27 +size 23560192 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..e84fb1b476d2528502fd105e0fda58c6d87a6bb2 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b15e84234ae65aeb47d8feb581ee33352202764e364a90f70ce7f9ebcb0d47 +size 26869760 diff --git a/params_shard_400.bin b/params_shard_400.bin new file mode 100644 index 0000000000000000000000000000000000000000..70fd19ec0f11272f309e2a92debc108514dba279 --- /dev/null +++ b/params_shard_400.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5eff5d7fbefb99a7d8780e8d25633d8ddd5c35cc282280303d8b65ceff71737 +size 93978624 diff --git a/params_shard_401.bin b/params_shard_401.bin new file mode 100644 index 0000000000000000000000000000000000000000..796d0c4c3e5642cc52943c84d0436deb23a1dbba --- /dev/null +++ b/params_shard_401.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f932ce0fe8fa9189087f770aa02fe59a27cf0d2c6071d975ec0078879b7f3b +size 188088320 diff --git a/params_shard_402.bin b/params_shard_402.bin new file mode 100644 index 0000000000000000000000000000000000000000..a1a1b846556be768176e49aa5f92142b2d997111 --- /dev/null +++ b/params_shard_402.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27dddd2099924ac5b3d3823d40ee6e63fe3ac67f221053bcff82bbf0a0e348d1 +size 23511040 diff --git a/params_shard_403.bin b/params_shard_403.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3400e7c9276245699a13bda826aa0b2d79adaf8 --- /dev/null +++ b/params_shard_403.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cbb8a11e6216a4c2a58ebe0b1df158a066cabad575666cef02fe4959607bf62 +size 33587200 diff --git a/params_shard_404.bin b/params_shard_404.bin new file mode 100644 index 0000000000000000000000000000000000000000..88570507fd658307de52b9c42e12729bf5715ae7 --- /dev/null +++ b/params_shard_404.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edda3f57dbfdc86baaf9d5e81fbc3b4f477b3c811405d701e6fc1dcd78799081 +size 26869760 diff --git a/params_shard_405.bin b/params_shard_405.bin new file mode 100644 index 0000000000000000000000000000000000000000..235c0e653bcfa01545d11ef2960de95b9cd95b94 --- /dev/null +++ b/params_shard_405.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e83433dd5c6e844e99fe03cc32c6bcaf14a8dfc7ad39ea20070086fb2cf592d +size 93978624 diff --git a/params_shard_406.bin b/params_shard_406.bin new file mode 100644 index 0000000000000000000000000000000000000000..192d631519005dcfdf6d23095272f47a85443f3a --- /dev/null +++ b/params_shard_406.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:915384f7010adcf9e771e8afdd77b3fb156045b889364701626e1cca12be3dbe +size 31100928 diff --git a/params_shard_407.bin b/params_shard_407.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b99539db683d538e084eb7c78515a3f98b4d363 --- /dev/null +++ b/params_shard_407.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5831a7a8531b0a959d35354c211c3b2eb30fe4c44998c876f6ab5b18c5545d44 +size 188088320 diff --git a/params_shard_408.bin b/params_shard_408.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb6bf5731840bb17f31b5c3367aac3e9a231db52 --- /dev/null +++ b/params_shard_408.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44061c053520e4ab24b6a224f1298114aa83a0c75ab2627e7a5f5ea5d6254d9b +size 23511040 diff --git a/params_shard_409.bin b/params_shard_409.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3a94a3b9c7a501d0a05f14d3f78efaa3b2170e2 --- /dev/null +++ b/params_shard_409.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011b4a5a4fdea501489efe5f92a84062b9210e34fc7a1d892fcca62f73245d2d +size 33587200 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..e0a60a59c0ba84b0b108b4d40f5883ceda3e4cc0 --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208597b9205f597e05a2ee2bcb01d2be392e329efce1bc117a9a4b64f4922f84 +size 93978624 diff --git a/params_shard_410.bin b/params_shard_410.bin new file mode 100644 index 0000000000000000000000000000000000000000..279eb5491824b7bac08fe550c0b7b2690d1930b3 --- /dev/null +++ b/params_shard_410.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fede166da0a5681493538fd954a495f8e86237ae769fe2aae393a9c6ff1730e +size 26869760 diff --git a/params_shard_411.bin b/params_shard_411.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d91f1ef628e12e63cdd65f935557badc6e3e26b --- /dev/null +++ b/params_shard_411.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b9ec03dd8f618579d2f040899195a0889be8e9454d6feb74d0e28b22df8175 +size 93978624 diff --git a/params_shard_412.bin b/params_shard_412.bin new file mode 100644 index 0000000000000000000000000000000000000000..069ec98b42d988c05e2232e4206a60af1949ace9 --- /dev/null +++ b/params_shard_412.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2867170e3001f3c9725cd840c91348a09a1462aaa4fcd5cd05cc5f4eb73245 +size 188088320 diff --git a/params_shard_413.bin b/params_shard_413.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ec14a930b9b112efc8d6427ba923ddfd7c9b319 --- /dev/null +++ b/params_shard_413.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c14586f68e0dcf9192ec4f67e5036f5fff4679cbfd010eb9c4253701c191d6d +size 23511040 diff --git a/params_shard_414.bin b/params_shard_414.bin new file mode 100644 index 0000000000000000000000000000000000000000..4630a0a66f68e74dc168063594044563c17d1c76 --- /dev/null +++ b/params_shard_414.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574ab35326db0ebb2e581862d3ba4aef4a527f7876ff7dce0b00f2e229de047d +size 33587200 diff --git a/params_shard_415.bin b/params_shard_415.bin new file mode 100644 index 0000000000000000000000000000000000000000..56e9b50eb960d55bdd6c3c3cbc183bced65d60c4 --- /dev/null +++ b/params_shard_415.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a4962c0d430e881206144d0ccc6a4b5f8933a49e9a98d393f2c9008917dec5 +size 31117312 diff --git a/params_shard_416.bin b/params_shard_416.bin new file mode 100644 index 0000000000000000000000000000000000000000..3549cd5909e6d2fe628ebc2e01a0f52c38bab0fe --- /dev/null +++ b/params_shard_416.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58cb17b1f6c14628b68870415c7c3dc836b02028eed97d86dff9ea2399c289d7 +size 31068160 diff --git a/params_shard_417.bin b/params_shard_417.bin new file mode 100644 index 0000000000000000000000000000000000000000..27271b6e42c5d36061d72553192101b9411eeefd --- /dev/null +++ b/params_shard_417.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d42288ba6a4d5ed5e5a95ee80f485ba1730a6e50910b00bba2846a321683642 +size 93978624 diff --git a/params_shard_418.bin b/params_shard_418.bin new file mode 100644 index 0000000000000000000000000000000000000000..2cee062515613aa07977aa82504bff501ad16fd6 --- /dev/null +++ b/params_shard_418.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c8b868a00ec952f65b685c1181a8184787bdac6eca58309ff171c8bab7bc11 +size 188088320 diff --git a/params_shard_419.bin b/params_shard_419.bin new file mode 100644 index 0000000000000000000000000000000000000000..8a44880941f0c08f0c995bb4d4e22f1b6df5749a --- /dev/null +++ b/params_shard_419.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54eab3721d4dc6d1b9d9d55a17c5c259d4cf10090e8ef9fbc6dd2ff74b0c20e2 +size 23511040 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..49e28d8284ffdd7d146c20d64e6b5e806df226e1 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351a4636d78742561d2b1fcb62f3040360cf013e639d8de2c3f9c3f15a1e2af2 +size 188088320 diff --git a/params_shard_420.bin b/params_shard_420.bin new file mode 100644 index 0000000000000000000000000000000000000000..7b992a277a5cb4d4642dbdf490bb824ae5817605 --- /dev/null +++ b/params_shard_420.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392b54cc92574c635550b35adfe6b623e83205b511ca97c298f3cb5d1f423496 +size 33587200 diff --git a/params_shard_421.bin b/params_shard_421.bin new file mode 100644 index 0000000000000000000000000000000000000000..e183d99ee8d03a5488a28a3b925de494ddb0f7ed --- /dev/null +++ b/params_shard_421.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12bf7b9923fe94287c51f0737079daba6b83826691d396172c833227cd3112ec +size 26869760 diff --git a/params_shard_422.bin b/params_shard_422.bin new file mode 100644 index 0000000000000000000000000000000000000000..7060b2942fd2545fa0b393808d502598ffbef8ec --- /dev/null +++ b/params_shard_422.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c892ee63da9e53ada7525e31c2ae5e4e71c9300f832192a04e6b8e24b5e1fa2b +size 188088320 diff --git a/params_shard_423.bin b/params_shard_423.bin new file mode 100644 index 0000000000000000000000000000000000000000..8693abd25b68f099bff88f73f2abbfe55f9cb45e --- /dev/null +++ b/params_shard_423.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6496fbfcd905519cb51da1368f4909cd065ae7acf8796fdd2b0ce9abe6a9f576 +size 23511040 diff --git a/params_shard_424.bin b/params_shard_424.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e39ee79d5956ba8c9e494ebbfe033e89adb611e --- /dev/null +++ b/params_shard_424.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0141ed06443d22bc90e3fb4ce563a92b1bd2ce769ba41963e7e243f8887eb723 +size 33587200 diff --git a/params_shard_425.bin b/params_shard_425.bin new file mode 100644 index 0000000000000000000000000000000000000000..0a3f391fc184b78abba56d08245c4841214fdf51 --- /dev/null +++ b/params_shard_425.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca09dff6f79e096c1abf9dfa1f81daa5e86e5c79a563357e025a0d8766463ee7 +size 26869760 diff --git a/params_shard_426.bin b/params_shard_426.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ee632395df56fa1b0f7e5701d1510de6c8f3f5e --- /dev/null +++ b/params_shard_426.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48518ed59c514a84b4d0486ccc8aede39bb1237ba3ee5bc15f0ccf39daae5b79 +size 93978624 diff --git a/params_shard_427.bin b/params_shard_427.bin new file mode 100644 index 0000000000000000000000000000000000000000..bde9347258504a1b42b87b0ff899ad8d8a6c985f --- /dev/null +++ b/params_shard_427.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65bc767c6639cc68b933c47bafbf07dacf84b80a0a1f52385510cba49f4c8341 +size 30269440 diff --git a/params_shard_428.bin b/params_shard_428.bin new file mode 100644 index 0000000000000000000000000000000000000000..d70a291769d82e1ae1d6377f855713f6accecc9d --- /dev/null +++ b/params_shard_428.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839270f5d1373cd31eba8cfa5d9cb122671e024ec643eeadb7db8a2c0fb7aaee +size 93978624 diff --git a/params_shard_429.bin b/params_shard_429.bin new file mode 100644 index 0000000000000000000000000000000000000000..7fdb8d7a6493a921c1b2577e72f4a980aabfc4fe --- /dev/null +++ b/params_shard_429.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f3c98bb16d7aa1908f40318e863df35e52f137f63b1da868c45e7d5618431e8 +size 188088320 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..c7f6f97dbd24c3d84431694f74d8c0ea6644ad52 --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf7c208ccbc542e74447edf191e727644f4d99f710127f552619b446f71bafc +size 23511040 diff --git a/params_shard_430.bin b/params_shard_430.bin new file mode 100644 index 0000000000000000000000000000000000000000..05695a7351c3a880ba79202a3757e11641730dd6 --- /dev/null +++ b/params_shard_430.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b623eb37a998d4fcff29ceda2c1057092d303a7e265f826c98ccbad25411f6c1 +size 23511040 diff --git a/params_shard_431.bin b/params_shard_431.bin new file mode 100644 index 0000000000000000000000000000000000000000..b232851da288e58479beb41b98327994e6511aee --- /dev/null +++ b/params_shard_431.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e001e0f40d4cf969c61730004fb786e38c02e3dfadd699e8c6e79eb4a9d1e443 +size 33587200 diff --git a/params_shard_432.bin b/params_shard_432.bin new file mode 100644 index 0000000000000000000000000000000000000000..c160cda7ddcf7789a830b77254de3e2edb55eee3 --- /dev/null +++ b/params_shard_432.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9deb5c8a7bf0a48a104b14d42be6f75c63c0bf4987a9d9a28832784f7228617e +size 26869760 diff --git a/params_shard_433.bin b/params_shard_433.bin new file mode 100644 index 0000000000000000000000000000000000000000..0885d7502c05d472e2cdcba3f659b6a1d625bf42 --- /dev/null +++ b/params_shard_433.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ec609b1a17ea89c134322e2b9fc4537fbe9ce3ab5fdffa4e59a0220077d1aea +size 93978624 diff --git a/params_shard_434.bin b/params_shard_434.bin new file mode 100644 index 0000000000000000000000000000000000000000..657130e88cd815101e2ed701ad5f801e5b9836b3 --- /dev/null +++ b/params_shard_434.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54dfbf6ebe275cf03129f9f5086ef3f81bda9739bb401b64a46ed6b87b54a551 +size 31117312 diff --git a/params_shard_435.bin b/params_shard_435.bin new file mode 100644 index 0000000000000000000000000000000000000000..00dbff56b83c26cfddd909f43ae32043c78c5ad6 --- /dev/null +++ b/params_shard_435.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99137661a6f16cb78f866cf3ce44be955f4115455887ef97adb6cdd5b6ed757 +size 188088320 diff --git a/params_shard_436.bin b/params_shard_436.bin new file mode 100644 index 0000000000000000000000000000000000000000..976c7b29b753f01dbb9011c1e3a7ba1127bc685b --- /dev/null +++ b/params_shard_436.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b393e1f40eb30eaca785dd9e0c078d25ac5bfbe8401ae412630fc18ad453e6cb +size 23511040 diff --git a/params_shard_437.bin b/params_shard_437.bin new file mode 100644 index 0000000000000000000000000000000000000000..98ba629735b176691c6140138a583efd4071dee1 --- /dev/null +++ b/params_shard_437.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:237f26cd4b55591cfb779ae8cdd9add6d0b02f41584108f1507a9b12b7eb6124 +size 33587200 diff --git a/params_shard_438.bin b/params_shard_438.bin new file mode 100644 index 0000000000000000000000000000000000000000..bea19debf60824289842e581c17f53ee323d3d1d --- /dev/null +++ b/params_shard_438.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e48b71e7416341ca539d92e5d2fc1033feaf859b634b78dbdb6bbf9d447403e9 +size 26869760 diff --git a/params_shard_439.bin b/params_shard_439.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef1058913ad286788c7176557618106929b1c192 --- /dev/null +++ b/params_shard_439.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:522a9692748cd9ef397d9d0152597c944d8d476c267b497b44aee2c7008a9e00 +size 33587200 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..b8a07518b9f0a5440d2d0a4eeb8693b45abad62c --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e68790defff7256b29b5efccb8a02be30d27e769d7394987b4f5c53db2cece1b +size 33587200 diff --git a/params_shard_440.bin b/params_shard_440.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ebb10404d02b9085925bb97c2fe3600f1e5c82a --- /dev/null +++ b/params_shard_440.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac921f10922cc50bd566924b150dc6c2143ef66a87a8155a082e547c3955132 +size 26869760 diff --git a/params_shard_441.bin b/params_shard_441.bin new file mode 100644 index 0000000000000000000000000000000000000000..1da536e390805537d7cf45dac94146a4d3734fa6 --- /dev/null +++ b/params_shard_441.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ee45dd9216181469f4ca56002d9f5e0a6c2dca3aa4dfd2d512c540051954040 +size 93978624 diff --git a/params_shard_442.bin b/params_shard_442.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c35d946d0e2b61952297720b6152d15ad752f24 --- /dev/null +++ b/params_shard_442.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ce443dcec1a7bc1857363c226a78ba6a46a8a2c58fd61a2bc17be3fe64bc1a +size 26894336 diff --git a/params_shard_443.bin b/params_shard_443.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecbfab6c5b118c01c8d254feccfff9902e9a291b --- /dev/null +++ b/params_shard_443.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7099f8f351dacb8a271ec488bd69d2d2ad9ffa6b7fa3368a9d9712982d87b69b +size 188088320 diff --git a/params_shard_444.bin b/params_shard_444.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c39bedbee21f7fe5c44ba6208c89128d464610e --- /dev/null +++ b/params_shard_444.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af8a527e12bac0966cbc692001b673cd6ba0e0a0af92f6fdd6a21c931810c84 +size 23511040 diff --git a/params_shard_445.bin b/params_shard_445.bin new file mode 100644 index 0000000000000000000000000000000000000000..1aa50ea54cf2ab8c465d60deaf010601ce4d8c51 --- /dev/null +++ b/params_shard_445.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b081217f073511c2cb4d4729e3d9dff0a73fbf3cc4e0d5987a8aac60dd3e2aa2 +size 93978624 diff --git a/params_shard_446.bin b/params_shard_446.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1aea9adc35df6ebb40edf46f7d23c21348001ab --- /dev/null +++ b/params_shard_446.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5a76e178e0a66e26c5a61f8d288ced8e8392de7d3bb931f171e926cd24af48 +size 188088320 diff --git a/params_shard_447.bin b/params_shard_447.bin new file mode 100644 index 0000000000000000000000000000000000000000..58354d6306b05b7286289f8c5e206474d798af1a --- /dev/null +++ b/params_shard_447.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a37468ad8a347e84a4f552f720c9de265ed91340fe1fd3c4c146761fcd828ce +size 23511040 diff --git a/params_shard_448.bin b/params_shard_448.bin new file mode 100644 index 0000000000000000000000000000000000000000..19f0d1365fe1765de53a0e4c52d1bf64bee14faf --- /dev/null +++ b/params_shard_448.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06eb3092398a6f058b8216d5868915426e3ea7ef255e9a0a821d9b9b3cd4d32 +size 33587200 diff --git a/params_shard_449.bin b/params_shard_449.bin new file mode 100644 index 0000000000000000000000000000000000000000..e2151409fd89bc7dcc4b40abd1d7239873c2c7d7 --- /dev/null +++ b/params_shard_449.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6cc375f41dfb518b393dc9fb5b2339371d9348d9eea3b84d2880d9dca66ac3 +size 26869760 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..4adebaa7ff6a84af4b0f81146a4f1ebc59644969 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe4bac7efe3c80f022d823bc8b88bc8c02920bac662be7e9e99c23555fe2242 +size 31100928 diff --git a/params_shard_450.bin b/params_shard_450.bin new file mode 100644 index 0000000000000000000000000000000000000000..118a9807aab0046819b1ed5ab2fe0dee95918144 --- /dev/null +++ b/params_shard_450.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f64b370a48e91aff3739ff51f657adab1cfd1d19defe10a4d72588df67786c5 +size 93978624 diff --git a/params_shard_451.bin b/params_shard_451.bin new file mode 100644 index 0000000000000000000000000000000000000000..aea6e5474068ee24aff0cbb45f93db035dbadee6 --- /dev/null +++ b/params_shard_451.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c23b2ae4896bd65b8f9c1c5d00a0008f7e165162a0dae865696f3ad21f22b56 +size 31100928 diff --git a/params_shard_452.bin b/params_shard_452.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea80f8c25b036594aafae1b88ad0d323e3435c1b --- /dev/null +++ b/params_shard_452.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384756a42a68443ed23b189dfdfee20c2213d08e512e597649c89750bc9fef14 +size 33587200 diff --git a/params_shard_453.bin b/params_shard_453.bin new file mode 100644 index 0000000000000000000000000000000000000000..91debfaf19b6929aa922213978daafee02700b73 --- /dev/null +++ b/params_shard_453.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf5bfaf2138be01d58b0fe50e64ac172ca46d41af69db5689a339c0d0292900 +size 26869760 diff --git a/params_shard_454.bin b/params_shard_454.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d82d9bed9e66a54110f9fa2f4da7bd1e8d1793c --- /dev/null +++ b/params_shard_454.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b926b7a7b9275ee686aebb3c2c7f3736a52d8158fc8315b193f6a60bbcd409 +size 19304448 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7b7e3c7efe84935265e64cde21b9f8ffe439e78 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9aef6d30d47cf23717a7d90ea80991eb09df70672dbb88cf688561a253b5ca9 +size 31068160 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..ca558b65b1a22bb62ea09f2c5cce229ced5fc32e --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd904224ac80d1a90556a6a71dd1908c000fe7bd016d23bf6b9f61263917ace2 +size 33587200 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..90c74930a457f13191d2c0350290992b2214d1c0 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f148bb5f1f8dd1cb7137040d3c19ea2328b916851f993cb5f4a7ebb0a063d2 +size 26869760 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..6dba1405f794c1613367ed5d27cb626ab713067b --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99481c70a27dceafb9213051beaef8417058926410102cdec0d873320493935 +size 93978624 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..38713203d7d29f5df4ff5366c70fa1c1719c897b --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d94777ce58d245b80f8873f1b431139e52fda0b340d0f0a76f3f59fd6af125 +size 188088320 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..26171fa7093f0955e71146893b329b4d50fae053 --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e020c77605b938601fdddab5b6c669cf5af579a068b75d0c0cd7eaf80bab46 +size 188088320 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..04ec95d036b8eb447ff54b6a534140c00085e7e8 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5bfc0c818c4da896a781284e39644074ad3b42ffbf11fe004a5c793c2d678b +size 23511040 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d5e39b45db8188aa19ddcc89e68a143a6212d9c --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074e39c65783c79117d54f8a6e251387e406fb2acaeb37a6776dfb99e5abf6b8 +size 93978624 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..17d299d1171424bed9048e8b6e84e0ca05b3d95d --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36c1668f2dcb294946bae8a20ac90684bb726738355d8e023517c8a9d514890 +size 22712320 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..017d970c891b473f2b4d38107184402f9cbaf414 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b3a3270d9f4706c5ed8b784f64dfaccca387132387e80e72050fa7c629d759 +size 188088320 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..611833a1382eb3ba6664e0a147cb5b08ce28e47a --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aea8173b01a09c342f2fd76c6be41b778dcaf8e46150ec87911992af55cdf1a +size 23511040 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..0316d6cec1fd3f945d4fc8c56e3ddf3ba4d8006e --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55682cb256e418f342e6fed5408e8cc1b3ac6ee0e5bc1f90cc9c2ac9fa44dfb1 +size 93978624 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..f688ce2b6057cc13e8d487271dfb0e9afcce27dc --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88871d15ccfcc4f9083f310862f7c56db24331cd4847ea0bdb1397469fdce4f +size 188088320 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..e54609a2e453791070b3649d0ba2ea8a9e17abcd --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e8a4197ef215aed13e051c1ce074ed3bcc94e80709ed1fb5d782b15ff2e7002 +size 23511040 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..8323d40f99603edbbb7ec91907d207ad2fde7786 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2a7bc3f393e803af733cef8e3b69510a154694f1a48b7643161f3b38928ab2 +size 33587200 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..58b92dbd7fd0bb90f85aefdb67a4712be1c4a944 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b1d0cb41a2b89c687dada47352b7a8da4497b505d258626828d639ea051ee5 +size 23511040 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d513d3a328817e34f00105f7bd021d50fd5fc8b --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fec51527dcc63acad86d9142337e389d2602f6dc01d3d3130aa759917fb91b63 +size 26869760 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..7bdeee460e19f79284eef4d3e97878bf9afbb504 --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf64fab4f4985307dda99a22f5bc609d252aac53004f4177ef4db3b9812e77de +size 93978624 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f8eeeb5296411fdcf58e23e12f266df94cd3002 --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c5e3fe9476138d8950c8facd084cb8c4cdce436f3bad25822402587f90b9e2 +size 31100928 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..df2962407303711eb126ad249f6e484a04d5ac23 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecea32ec41b4203fa9ead8aaa6bf246f1d46fce7cfe5376e57ec5439986fec12 +size 188088320 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..ccc940813f86e8d1d3ebeee8fae9dc274d2f877d --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91808871415d10f0b784fe87304f0dfb5a16d8610ce456042fb04d99a213f9d +size 23511040 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..47961885f422a6fe8cc91112aca4d8c71c131f1f --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e18d737283a947f7b5b018d2a72b3395f2cc396affc829cc96402e275fa5acc +size 33587200 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..638c89850ed6af52906d5fee7f4f28a0a9adfcf5 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196e8957d5f96d0dddafb9fdd22e5e62934ad6f1cf5a5c5dcc5807f7e87a14d0 +size 26869760 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..9f89ddec681fc6022283e075bdc3c88acdd49f80 --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45fc23eca6f6fb5fb7568b7c71448a88d1fbd2160be8fafda264262ab43d97a4 +size 93978624 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c6dd879a2a13c2b8e4ff87dbfc2f3abfb95f0c3 --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c1d80a07560d1230245c1da8fb1ddfd03a1c25462ad8eaeeebe83254fe1a2e +size 188088320 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..7943dfc0190f1f55f16c55e7e6c0ec0398dbe1ff --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5ae7572e8ac0f33275e1a44c9405dbc6af910f8179639d96793dcbcfb2b339 +size 23511040 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..3865b95077dbc5e4225676313134e1b33a5775cd --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:695227a30bb137223ef9ce4f197656cf9ba87f064908f61d307e68afbbda07be +size 33587200 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..c7aad289fd2d7c8856893b8292096e45c45f6291 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e846fb6e3729dd723133ab2a029c20db09cd7b0551ca55e5b3ca82dd198954b +size 33587200 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..7988d37187d4c0d1ec42e3f512fd3e1ed0446109 --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37eeb3e1609301d5e345af6cf6b6b7cd3cfb091f8203fbbf8debba351ef48def +size 31117312 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..41908b83653a310e6d2bea4bde6667af1b289dae --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5277bc65d9f698357d58544145ad572b4d8de612b167fccd245771b9645cb959 +size 31068160 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..0348e3aa20c081170981f8f676d3e8bbce32f392 --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d668f6185352deb15e81e275888023da9def57bb8486a04d21c98395a60c03b +size 93978624 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..ffba2c4e243f4905624d0f0d27cb85b938c95091 --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7db629e9a5b0b34a49aa7a2ecc8412b60950e36236dcdecc3744827f730fb18 +size 188088320 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd81a8b23a97cb4d563424d61e77965064c2935e --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5064dc8961aa92fea5fcf9d9e63bd9166e4c49877ae943c26fe1e553bef9b236 +size 23511040 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..28af70a3316f8b1863d4376c81f7d85747288931 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f35226e739d55daee3e445d84c243c111558df9fecb01b41e3c5fc05281a22b2 +size 33587200 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..9144523160b3f23bbc4ea18bd90a392f6d5ae4ee --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a735bb5972c36b12d81f19b5f4c3e311cc55b472b5d726d8a7dc03ac045a6ad3 +size 26869760 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ca62936f5d136d755fb42e34f445a829d0da856 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b329a4538234c1db98236174aeba8eabe464b8b2b0bed7c55f3fece7c44472c +size 188088320 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..c0ff314250c526d823b91cfc78f680b996df9fd5 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ab69aa61bb743d70e5048cd23a71f1356a7c72dd0db260308666b3def8c0231 +size 23511040 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..690a1f54a9d7e2d538ec328ea8f1fb549dc16863 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77bd14c119701da0a3be9404be9e61cdb9dcadc7ea6428442e46bbbe05e6363f +size 26869760 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..a30d9d60eef8e7397f1eaff6ed485bd9dcb7e8ff --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:293495a761850c170e1aa311b607ae0ac0868348bdae8c34edcfe3867a29c101 +size 33587200 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..c90c8795330a4375b2d494a4ba5fca1fbe42ef70 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4890b2819e9a5a4a2f67e91c87b2ba3762b92fde3910a571e2a5f6720a56c0b3 +size 26869760 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..a79d4532b2d8cd991971acb4e171dd72593078e7 --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:651ec60a9e077c0425bc938844d5038451cf2b3d32452aad0a4381144f4cb19e +size 93978624 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..6508f7988b253e3e73164f86e8c27f462ca8c47b --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c887e51d2631bd26a4622d9e234b32ebc7ba5b53b5e9960ccc3aae02404865d +size 30269440 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc5bbd97df0226849888b94ad4fb572b227a1f1e --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac95941479349b3224dd87e3650b431cc1fcdffd9b46a127856a5a90c437914 +size 93978624 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..51325ee81d647bf792ad68a363c7c319d25e26a7 --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98996ba326c0ff90964333cb1e553447b62a3fc9bc144f2b3811896b6c3dbf2c +size 188088320 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..118234f1c356e5fcbf3816fb33f02ff696160db6 --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee7d7735277be9c90c75fe766cdb5db767ed2aedf0a95b1752c929528e021f53 +size 23511040 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b6e64576318d6232ca8fcad5197bf0be740a10d --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff2f4b33ee8cfdc6ed613813a0bbe6ce67d752c8ec608053d910850e10e7a34 +size 33587200 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..898911c933389a96501ea1ab8ea5c4a2cf79ef89 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d10b020e4c68382c056847f5b432bf9550d88b19d8a7658e5ec206009140e242 +size 26869760 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..24ec7ed77b17dcfb49988ecdff2d9d2d2da78ae8 --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d248e9dfa0f262461a300b0ff37df4755abcf5bf85c6682659b900fe034dfad7 +size 93978624 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..5819bf020cccb47240e85587e85b3899c85a048a --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f5410e086f4d4b7904be47adcf83fb17ec99d687df7afc929a14fd4f2d0f012 +size 420679680 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..d67b0ef1e990ca1b6e2748ef39539d70666dcf0d --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a242b89856d26ecbd3ccdba25d0d153a01a6385e2b835846922e144cabf31c +size 31117312 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..89ea84e81ac4911228aba9202066fa137335efde --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b76ebf42032533d7c92b6fae24419fcd520d4a734dda4f697cb9eb4ef49fe15 +size 188088320 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d814eeb29a26fc9e6db960e10e1df400d95029b --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9f00418f41c665e272d85f0794dc0a185d6c9a464978d2956d8bc5161cf229 +size 23511040 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..a5ec99ee34f505109cec7ab0f27bfb45e0b61526 --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d3bd727ac2880aef6bee925d0314598b55b56c2dcf552ae7415148d8fbcdf3 +size 33587200 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c041817cffd16cdd6bc36361ea5dc6ba1819e81 --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a5e32e00c18f3c6cac0eceb55d196020b2020072b8264aa9e72508515c7f58 +size 26869760 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..77d9df420bc8f9f62c12221548f2e6ae955b1a8f --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff379af608ce92032607f34889a83651329978e92356ba484352addf0bdc3c0 +size 33587200 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1bd571c8a835d02664a0fe656ab89ab3642840e --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29cd6d37989168a99a79404a0c37afc843093d487b4af2af598c8c921f41062a +size 26869760 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..80e458717d0c0ed5447272dd4a45cc1062840c46 --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:432f8fcfb2ad353aa90653bf4ecf0429d133eb8ef3f8d647645064be8d017e6b +size 93978624 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e4d7cb7b3070a9b932eb12374fdf24c3153abe8 --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72cc8022be2526a4c7e56398f83b26ec9aba0e354d376d8a6b4ebcde310805b5 +size 26894336 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..80bb9b51560eb3a10af43d60637c2e04098e34a6 --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8602c92e98b627b4376c98b590e0fb1d013fc65e9c1768a8ab44508cdbfc2d0 +size 188088320 diff --git a/private-llm-config.json b/private-llm-config.json new file mode 100644 index 0000000000000000000000000000000000000000..7b2148c2d0beab006a2ee7bf990e034cd0196fae --- /dev/null +++ b/private-llm-config.json @@ -0,0 +1,51 @@ +{ + "model_type": "llama", + "quantization": "w3a16g40sym", + "model_config": { + "hidden_size": 8192, + "intermediate_size": 28672, + "num_attention_heads": 64, + "num_hidden_layers": 80, + "rms_norm_eps": 1e-05, + "vocab_size": 128256, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "context_window_size": 4096, + "prefill_chunk_size": 128, + "num_key_value_heads": 8, + "head_dim": 128, + "tensor_parallel_shards": 1, + "pipeline_parallel_stages": 1, + "max_batch_size": 80 + }, + "vocab_size": 128256, + "context_window_size": 4096, + "sliding_window_size": -1, + "prefill_chunk_size": 128, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "mean_gen_len": 128, + "max_gen_len": 512, + "shift_fill_factor": 0.3, + "temperature": 0.6, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.0, + "top_p": 0.95, + "conv_template": "deepseek-r1", + "pad_token_id": 0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "tokenizer_files": [ + "tokenizer.json", + "tokenizer_config.json" + ], + "version": "0.1.0" +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..4f47952a1bdada713048f5e45fd3b52ad615fb34 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86 +size 17209530 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..11176da679c2fc9d85d25326f2a9a419b2cf189b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2067 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "128000": { + "content": "<|begin▁of▁sentence|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end▁of▁sentence|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|User|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "<|Assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "<|▁pad▁|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin▁of▁sentence|>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|end▁of▁sentence|>", + "extra_special_tokens": {}, + "legacy": false, + "model_max_length": 16384, + "pad_token": "<|end▁of▁sentence|>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}