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..8db36482fd18f6e30254f4119ca27634840bc7b4 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,11 @@ --- +language: +- en license: mit +base_model: huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated +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-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated) 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..2d7a8e4b07904e929e953fdb8a8df91e0aad5859 --- /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": "c8f48cea1c953e182c8f0ffef06d4238" + }, + { + "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": "481d39272d969a99061589a30d9fe5a7" + }, + { + "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": "8d9aa2da7ef0d186919694290fa169d3" + }, + { + "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": "fd8c1ca4e556368cd1fa4ce83471eafb" + }, + { + "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": "6dc699d36850fe5d9bf7d79880e6a7e7" + }, + { + "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": "fc6a4bce2235d8767ddbe612003a4180" + }, + { + "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": "a1282147152a068b385f25b4f40bf103" + }, + { + "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": "6163be61d9e07c65f01c99c4e5ad4539" + }, + { + "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": "3c1703af70e72a003f81e2a806c47e68" + }, + { + "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": "e219f8f9edf4adcafea76b94d010ad1d" + }, + { + "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": "5a84bebe6da3fefac7ebcfe8db9e3d2a" + }, + { + "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": "9632665694a636664832e0c7bb700a44" + }, + { + "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": "2b200e951b3815008fa98cfeae9a540d" + }, + { + "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": "fbba44257a548692a5270108d530f974" + }, + { + "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": "bf5a46f5e327561fb39d36ea09dcea85" + }, + { + "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": "6170fea86768bcc39743eae2847e8fba" + }, + { + "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": "983c6d17409074bdfb11dabefb99dcf6" + }, + { + "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": "cb494fee1dad306dbe952dc37a78257f" + }, + { + "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": "f36910f6711d3d0f2ebbfc7595fc216e" + }, + { + "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": "dae2f8881fede83c20471b9f3ab683b6" + }, + { + "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": "f93d35ac94de62abb6bd7e29c2cfed0b" + }, + { + "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": "48e6ef5def924c93bbe07bb3c2b7d4c9" + }, + { + "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": "ef0f0d783bf9d0abff69b9265298b9b9" + }, + { + "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": "7f36d4b540b023c464a6a3b92f013430" + }, + { + "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": "e901f4e255af0cc734fc8c7946fa8057" + }, + { + "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": "4274fd6a80f71e57c7c3b6b617e9a917" + }, + { + "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": "dc490fe2a1c7ad67a31148350e71968a" + }, + { + "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": "c1d882ac5a3c4cb7dc08d19fb0195350" + }, + { + "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": "019456d7666b2a63e43b4fde92715264" + }, + { + "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": "53d140d73e1aa15b047ffc42e99e60cd" + }, + { + "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": "0f2f6a53d1bbc4e0fddd8ba9b4e62532" + }, + { + "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": "5ddfa7cd855ec86b7b5dd4d458eec3a7" + }, + { + "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": "67328f7a926cfad5336e4d1651414a8b" + }, + { + "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": "1a77f2183e8b740cb47ea08e5698c7b1" + }, + { + "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": "5aa0a4603c926f68b485835bd8608023" + }, + { + "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": "0fe7b43c1983e3ccf2c3db03b9857559" + }, + { + "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": "15fa27c3da7bc629fbc370b7a0a2affa" + }, + { + "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": "a9d83ed4c83d2ae2571d60767fd63e8a" + }, + { + "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": "cb6a60c6ecebccaef4dcc815f690795a" + }, + { + "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": "95f74584ad503266fa9f7c0a06071bd7" + }, + { + "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": "f857e5c612e0140b3bc67f0abbe00231" + }, + { + "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": "689515643766b61043e13b2666d6a561" + }, + { + "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": "c2848987ddd835db9b484f89a4afd9cf" + }, + { + "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": "9c9ddbbab82f5954113e6ceb84460770" + }, + { + "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": "3dee722251b69ac4dff7f5de78b49824" + }, + { + "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": "30c981645305bacedd42c39fc08a3fb5" + }, + { + "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": "84733bf110ed2264357c7c4fe772e0a1" + }, + { + "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": "a02157cdc77a90869f482fcf2afe14f1" + }, + { + "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": "9d522f94f2caef87da90b112b034d0fd" + }, + { + "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": "0c50b0cf4126747af7627c2ad5771b5d" + }, + { + "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": "efbf4781132182d8dbea8e345cb5257d" + }, + { + "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": "52837043edbb1f78adfc94444e737631" + }, + { + "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": "203ed28df11deb72978d9402147be509" + }, + { + "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": "b9fa8e69282c7442efd91aba597e260d" + }, + { + "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": "9424ca1dde3c36b4221f8ed1c2c55388" + }, + { + "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": "ec8fa57e8079771c08f55c85e9e9647a" + }, + { + "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": "92b386b4fce190f2effc47377c8315cb" + }, + { + "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": "d381d3f4c974e949c07bbc07dd27c42e" + }, + { + "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": "ff110a6c15460ec16472d44c8b873629" + }, + { + "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": "fc9f5f681a8f2d5c27dbe3016cfeb28c" + }, + { + "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": "14836640bb910ab7cca8c3210fcfafa0" + }, + { + "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": "61d9f3070bae76a54814e05773408795" + }, + { + "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": "0ddc2a84f62d2c41cd116a31a110e5cd" + }, + { + "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": "f0aa4172d5451e98679c736b1e3c42c6" + }, + { + "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": "f7e9f82f7b194e038482b3f409b21add" + }, + { + "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": "68e2c3a15e8bb88a32b56170037a6201" + }, + { + "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": "1d15b082c7949435997d2d34e59ed10a" + }, + { + "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": "c00f3a4cde4f2b70866efd049d24e2d7" + }, + { + "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": "ba302ed4be03f2894304ec1b2815e80b" + }, + { + "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": "2fcae42f4aa2b7811ffaac0f892ab1ca" + }, + { + "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": "a9d5bb17840ae4e63664708069bf0113" + }, + { + "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": "b64554ae5dd3de3c245cda978b7be361" + }, + { + "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": "fe2a4cf57630aae1dfaaf36d4993359a" + }, + { + "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": "9b3f1ad916072a99aeeeb9f1840703bf" + }, + { + "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": "9bdcd0bce15d58d2bd9f496d9da08c79" + }, + { + "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": "6c2321fd5231794af3dfbefc82cf0568" + }, + { + "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": "82163c24f6a13b390306b1b14b2fe7aa" + }, + { + "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": "5d38ab0e6055b2293c84856aaf79a93f" + }, + { + "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": "b38918ee9f75a7bf06fd5adb10e788ce" + }, + { + "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": "fdb5e31dbd7baa85d6a8899cb2cade50" + }, + { + "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": "9546ba429cb9285f8ef563f77494291b" + }, + { + "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": "ae4dbae0d646fe02e1afd1bab8e26150" + }, + { + "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": "09fb17963360bfc4f6c3175c4e5a86df" + }, + { + "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": "185843ac28fe4afb3091d9f80ca650ae" + }, + { + "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": "7d208455888415f74eeca206d47d8d4a" + }, + { + "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": "ea4391fe2e1a871f194be2f9b8e59ceb" + }, + { + "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": "e36757b76c2338b50c071a380e70f0f3" + }, + { + "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": "a0df39acefaae67624ea23089552b324" + }, + { + "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": "2b3551247fdab08de6ee16cea5f63e60" + }, + { + "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": "5ea773e0007078030ca061891a1ada5c" + }, + { + "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": "418d40b0ca371fe87cdbfb260fe01637" + }, + { + "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": "7dea13c5eb155af994d95e29fc2907c9" + }, + { + "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": "a1570eadf3d98a5eeee5d97e3708e90c" + }, + { + "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": "cec37ff63a556f1903d345785cd585d6" + }, + { + "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": "b3e6054f1f3caa8aa8528a40e7dafd2e" + }, + { + "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": "125663124f0e333b70f220e04ff1063b" + }, + { + "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": "c718853f2512532e75536b83dbee71c3" + }, + { + "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": "1c2affbad59156ce5687e6fbd197a285" + }, + { + "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": "5d311c12e4ca725cc223cf40888fac95" + }, + { + "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": "3807c6ea3bc5676bc27ea0fa8fd1500a" + }, + { + "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": "5b30bfcb66056a8f7b004cb62c89d770" + }, + { + "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": "3589b56fb0ba790408ebcda25acb1050" + }, + { + "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": "0a273720a6a5bc812020c9e44a23b4c5" + }, + { + "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": "1d67e2d69c542b73f082f1624a3244cb" + }, + { + "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": "82a304d0b8d88aac812a8f2324a04f78" + }, + { + "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": "27049565b6134bff574c381bf61d2829" + }, + { + "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": "06bc26b29bcfdea8f9a3854520b414f6" + }, + { + "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": "26779675de91a46860e8a444352c172f" + }, + { + "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": "d841e318e056c3ed943e167b99029edd" + }, + { + "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": "ec791a8d97b7a3078f40cf213df72659" + }, + { + "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": "5f7ad7347f66c6fb2c02ef97f2d67c92" + }, + { + "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": "454b654f87206579cf2ee11279c851d1" + }, + { + "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": "a0c3844bdcb5fef309d035ab6ae4afeb" + }, + { + "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": "e4a0aaf57d1af0eb2440fee4475f682b" + }, + { + "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": "a451712ded80478d59e35eb819414906" + }, + { + "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": "b84e18222abc988882876206b42ccabd" + }, + { + "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": "d9bcec59a823b40eba5d23862f076cb3" + }, + { + "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": "ff8f0ab682ddd4a6035af482ffa6e924" + }, + { + "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": "4df3051a5a07c3768be62d7df31180d1" + }, + { + "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": "43dc27f76d4e00816415bfd99a93f8ff" + }, + { + "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": "ef6d8185b08409d70bdcaa867f6fbc23" + }, + { + "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": "33cbc143e18aaed8abfc7e3aece4d5f5" + }, + { + "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": "55c3458730b8f023186855ab1cdec443" + }, + { + "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": "36ea4ac92462dc4779b31d67276af488" + }, + { + "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": "7405e9eca0cc1276b49409f87012aee6" + }, + { + "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": "f0e202da4bde4fc33fa4677ecd4ff932" + }, + { + "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": "652ce4a84398a4e0c0f8890cd36121f8" + }, + { + "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": "7ea6108f35e6d1a3a00a6bf874e84fd2" + }, + { + "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": "025a616136bcc044cf20d68a993d00d7" + }, + { + "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": "0532bc8f6e58fa6e33803a31f6475de8" + }, + { + "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": "05ad08cb79931858799db7c0d8417ce2" + }, + { + "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": "4692cdf47131b60f157ae16fd483e405" + }, + { + "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": "54503d0a10a792af02aeb1e2ce4fc56a" + }, + { + "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": "04ac4037dc551b0327594d765db6651a" + }, + { + "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": "a96597d2963718bd76c64ef87217c7ed" + }, + { + "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": "4a45df3cd00fd584a24c8be9c4f35c14" + }, + { + "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": "cda33e0860c00da6b040bd1c566c0669" + }, + { + "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": "9e85e3451738f8c49ec6032a66ae6289" + }, + { + "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": "291ee41e446dbb0863ef0bed298801d9" + }, + { + "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": "922270f50cef1e83b5cb8b3afcc758a0" + }, + { + "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": "420629fe011af2fd32ba6ab9c5c3661e" + }, + { + "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": "121bcd1e31f186a71555fa795493b7f8" + }, + { + "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": "a08e042a4fc8f12f3fa2822ce98a6855" + }, + { + "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": "f1d295d70edf4d1f15e8e81f21d08f60" + }, + { + "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": "83e8a8881e94f08b8d92f5269d8b0e5a" + }, + { + "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": "9f8ab9942a7eba8eeef7ba1121e72f81" + }, + { + "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": "c5ed65168ab175f1abec8e77a8b9ecfb" + }, + { + "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": "9bfca638cc6c6989da30923b28babd37" + }, + { + "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": "757f74c445e592052596328a9ba19180" + }, + { + "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": "62c5fc1fcc653db981b57b91e7d369a3" + }, + { + "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": "cd263704e5c6e77aeff89d9e0d4742ef" + }, + { + "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": "45818221462bee619a13ebd9915bcd48" + }, + { + "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": "a2ace1cd44dd0e83794851569f8709d5" + }, + { + "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": "ab01fad2c270a766a6ce761dffe7a349" + }, + { + "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": "faebfb5b1f7fe209910d7ce560fe6bd3" + }, + { + "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": "c129e37e98dcda4cb51380c0576a4f40" + }, + { + "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": "df4ff64f6912816b450abe786884adf5" + }, + { + "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": "ce05f2952adff16a005ffbc8f1adbcf4" + }, + { + "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": "29a662089ec1c9353bb7b72650388d02" + }, + { + "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": "32585fbcf689e2cd039db5fba29bff0d" + }, + { + "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": "413abb8e200e05659e6b8712c280e0af" + }, + { + "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": "901c1d6d18b2d4e20031837720257ac7" + }, + { + "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": "ba5345576117d875b08b2a249c731744" + }, + { + "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": "0971cc5d45557bc71bf0bd25cf399951" + }, + { + "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": "88f4a60522dfaf77cde86868a8c719a7" + }, + { + "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": "772b1e29e49d24dd8b5b48513d398ae6" + }, + { + "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": "1aea52702fbba818ab084b83ac7a6632" + }, + { + "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": "70dfc729267537eab5957d8ca3e31054" + }, + { + "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": "21d65248969558ba2d63aec8b71b771c" + }, + { + "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": "5cb5589b3fdb4737876c9b6df0ffb383" + }, + { + "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": "24ce607df219fdae7250721f9bc77e3b" + }, + { + "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": "9b266efbccafe7f56bdff44f92cfba01" + }, + { + "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": "31a45ff57603ae8c1dd87766951c1ec9" + }, + { + "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": "dc6ae8fec930b703ef8bf2d545f2b552" + }, + { + "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": "1397d6e888e29857c3b3ab454bf1a1fc" + }, + { + "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": "0c654c5a370bbe9abb5e9ce442d22e6b" + }, + { + "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": "9b120821604b4fa20eb03f84f88852fe" + }, + { + "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": "61a0b8771d4a50547abe7eceaf75fe59" + }, + { + "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": "43ddb73ea46996f7c86611763d76f2c3" + }, + { + "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": "65663c013739964a03586d5b454fd9be" + }, + { + "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": "ec4de4eae3acc1b0f4fa5db0432bad8f" + }, + { + "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": "ba0b8b10f81fd62b98e8d67922eb9462" + }, + { + "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": "16a2f3ee60f241edb2eda709cc91b535" + }, + { + "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": "8b0b86807f2dc9a03e78429d8f0e071c" + }, + { + "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": "93d0694f71bbb08b808dab643230aa29" + }, + { + "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": "b3025f219003466e7e9951bc07cb02d9" + }, + { + "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": "ed921b9f11aa3930e44b93d07c0b4213" + }, + { + "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": "a3ec9a238ebdc5a640f1a130b35022a7" + }, + { + "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": "a9f3ef8daccf813b0be5715aefeda4d5" + }, + { + "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": "78ea3fd3bacc1a2a64877e46ea66be6b" + }, + { + "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": "e14f8588b00e2f75128d54616ebbd630" + }, + { + "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": "0f5e9b39ff9296b9b7b2a4a686a1384f" + }, + { + "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": "18965668e6c23008376ccfd40948af06" + }, + { + "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": "1e6bf1f2662bfe02d7158ecaad93b4aa" + }, + { + "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": "a682c5c99c980a3ffd83b16f196ad527" + }, + { + "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": "f2c0267a611cae3fa83a808b9b4618e4" + }, + { + "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": "aec631dfd5a6a5839854999bc0eb44a3" + }, + { + "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": "fcc20c232ec60fca20f3d063b46927c8" + }, + { + "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": "645ab0ad6b1c786cbd5200c391e99362" + }, + { + "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": "51aa0ddc3ea174ce0bff050e87bf42e0" + }, + { + "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": "46ed7ba15b020ea56d380c59f840e31f" + }, + { + "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": "097d7c729ca47d55ac7d9c0bfec515c5" + }, + { + "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": "23a53bd4763eb76e2bf59371b5ea26d3" + }, + { + "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": "5e837018a93035759c86bdd560320c60" + }, + { + "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": "f72d2a386f8b9d576f495effc73ca38f" + }, + { + "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": "9d3309fdb14398a9dc4d9a6106895259" + }, + { + "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": "50a165610fa43e4e2e21f86930086800" + }, + { + "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": "134cce50da37722c81b0d2104711a05f" + }, + { + "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": "3753a69687c2c1e4538b25e6d9508b7a" + }, + { + "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": "fe3e1f6c672e4227787eadc117d228ad" + }, + { + "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": "c7751359be7b69cafd5cf7df7f894523" + }, + { + "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": "a1b237478aba6feffb3c4fbc7b59cb0b" + }, + { + "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": "dae4a4740a236d02ef400b25d8560cfd" + }, + { + "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": "f1b4ece36b60b8aa7c7fb2d531354d21" + }, + { + "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": "4972798a24eba0019abb9a9ab3ad7bdc" + }, + { + "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": "90791285a5cf746c677a161b34e29696" + }, + { + "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": "257e41e7b42266b92d2607fa7ffd94b5" + }, + { + "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": "edf2be170a3bd098913be7636f06bfde" + }, + { + "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": "275bdde986225b3e326644f109c81faa" + }, + { + "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": "4f98ef8809b3d7c9aa78bdf2c5df9792" + }, + { + "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": "c3f262e54a3aea385f6068a122220593" + }, + { + "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": "28e9d23a03114f08969eefd4e03f3b49" + }, + { + "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": "13b67034cb8f30b0bda40f3e9317c92d" + }, + { + "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": "37b50fd19262a876f41a3cca4fc9dd14" + }, + { + "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": "4d9ebe3c20b3683a34a3aff1a2355f04" + }, + { + "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": "610ccac534fd1b5dd06a87d0adac832f" + }, + { + "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": "225ffca39bd380b132e05435fdd8fd25" + }, + { + "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": "ec8e913cf0740fc216be02696fd55c51" + }, + { + "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": "03ba71c6dd4182a4975a85c36e13eca3" + }, + { + "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": "abc40efdd62b446d3fbabfa3744cd88f" + }, + { + "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": "4eb91d62dfd52c207264d4c27c6845a5" + }, + { + "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": "d2c35b5a1ddd9ac11b8297694f8bb18c" + }, + { + "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": "ba3ebeffc900f9361e54e67c52f42648" + }, + { + "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": "1bc6a228316f2a2fcd15c314281e624d" + }, + { + "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": "afdffe3a88a18543095e06e0dfcfa0f0" + }, + { + "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": "78d0873363122e267f794629ef31633b" + }, + { + "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": "54f265b7494c59d22438e721ebe9cf17" + }, + { + "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": "6b5bbd118b7d0bbfbb7aaf47453f6c61" + }, + { + "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": "6e8a4eef1e8bc7d6209d5193956cd8ac" + }, + { + "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": "1077645a179bcfe49cd8b2145c04f98b" + }, + { + "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": "80f9cd6a5837994daa003ca4525cef43" + }, + { + "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": "ee766ff203513f9d47cf515b6ae4d7ff" + }, + { + "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": "49c1a36148e45e8363fd5121e59e2b8f" + }, + { + "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": "e087e6ed3a8987bb5d7492c317d75b94" + }, + { + "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": "78b0819bffdda78f849c2b2a0a935acb" + }, + { + "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": "cf370141bdb1c510ebf1b2f96c2f9388" + }, + { + "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": "1853687236262f3505554adc3d7e7ae6" + }, + { + "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": "f458060769f19577824e9bb38e71df1e" + }, + { + "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": "ea8485b2f9f9caf815fcf5de9b2cc1ce" + }, + { + "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": "7b29431d9583d087ca1e68ccc8420957" + }, + { + "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": "74eb222e2d9c828d9473d3f4ec21b599" + }, + { + "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": "8492199d952bafafec037b80ae61ed40" + }, + { + "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": "a167d433c10c27e0b9b7a6ef24010652" + }, + { + "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": "1301723aa96f70bb0b0119dcaae2c156" + }, + { + "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": "102c6127b5b848c1af95088aa892a6a3" + }, + { + "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": "24a8ff819cd21e192fa5e7b14a8d7655" + }, + { + "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": "8984fb9fe49d426d9077cb15d5ac991f" + }, + { + "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": "683c464767e58c14057d28f48e47ef47" + }, + { + "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": "bd9d70262ff6be8c42a342ce411aa0c1" + }, + { + "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": "02177aee68ebe0aa0b3e3c1633a305a9" + }, + { + "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": "5ed6f8e53883ee7ea70365da7578f569" + }, + { + "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": "0c4292f410952a89f0fa1f4bb8d48941" + }, + { + "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": "80b1af8f285ae28a3d8fcddd6a882e43" + }, + { + "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": "3a63c818f74a2cbb6db1291557a97922" + }, + { + "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": "a4c31911e705c0b47b503d3eef94d20a" + }, + { + "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": "8f89f42d4749629fdfbc94b4fdb33cd3" + }, + { + "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": "70ba58f4bd0f4dd6484eef525745cc2d" + }, + { + "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": "9238caef703e872451b6239f8d6a95b9" + }, + { + "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": "2124ae22c61719dd26acf8b27e4b304f" + }, + { + "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": "e12db8b719d1c5771516fcc702b844b1" + }, + { + "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": "947fd5389158a2ca97eec8b278c2c120" + }, + { + "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": "25fe46ee97399093a6460652d84a57f2" + }, + { + "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": "de94279c46928b9df0eddaf440271846" + }, + { + "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": "d6f390c709f920269bc85b39b95f3bc0" + }, + { + "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": "b4727dd22cd684dce907cc7b4b026c09" + }, + { + "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": "56848387da59990e61f8bfedb18dc614" + }, + { + "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": "d3cae51e985391520677d2688301a51a" + }, + { + "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": "467d324252d79ed36471928cd378e14a" + }, + { + "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": "75e28330e7ea1ddc753440785a0bd12a" + }, + { + "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": "41b05a9d9242987e82819d2ffa19e9e9" + }, + { + "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": "bff0160eb0b829e8f3814c73685bb04c" + }, + { + "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": "88cd69d1597dc741ac467cd6a9fcbc24" + }, + { + "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": "a17d8f24f01b1aad553c51c1fec00494" + }, + { + "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": "88f055b61aaf61a403d06cf8d4c2a119" + }, + { + "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": "a69a058dbd2fccdce9dce543526fdf53" + }, + { + "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": "854028ea616bdbe5cb7f5dabfe964f07" + }, + { + "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": "9aabb1898afd0b8c9cd34897355140c3" + }, + { + "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": "0e7404687b5002d7447e2e508ae40cdb" + }, + { + "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": "8c185b1431b298cd87345321e1d8c5b1" + }, + { + "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": "3af4129d6d52d14d171fbd816ccf757c" + }, + { + "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": "26121ea1edd6db5409533b97a568267b" + }, + { + "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": "cd74de2dc9df067670359b9f14b3eece" + }, + { + "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": "49fd10c35f42374b71227eb61de39865" + }, + { + "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": "b5da04eb808c597fcfbbd64b604f4b2e" + }, + { + "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": "9f442a1bce863459c2c565056b2ec52b" + }, + { + "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": "0630ab3e135b0430440c0d8476f5a9a8" + }, + { + "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": "a108fa86396cb059856072ec96bc2237" + }, + { + "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": "f17703d78454dbdd5f59c41c61fc5f80" + }, + { + "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": "535662148ba7edd777c81638a90c1d81" + }, + { + "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": "c22b6bc78a2a54295b0bb9fe72c4629a" + }, + { + "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": "51ac3cd008ada7254c76c5d32cf46780" + }, + { + "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": "5e5f495e7da227f0890bcc0261c18ad6" + }, + { + "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": "e8bef9221fb858dd3176c6ec330b240d" + }, + { + "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": "2eda77ce88575466b8ab551d08e69afa" + }, + { + "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": "f094869caf1757b7aaf465ff09df9044" + }, + { + "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": "bb989db56a3592e21fa331803d577abf" + }, + { + "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": "73159186480ae8cc0c122063b848bca3" + }, + { + "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": "3631cc9b260d624631fac0fb7aee487a" + }, + { + "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": "2b975de5103ab4826c95b1554577a3c3" + }, + { + "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": "1686e0d8ea6088499a100b1ec7645d8b" + }, + { + "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": "219ce5d38cbe08c3c2004d06a997884a" + }, + { + "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": "64cfb78cd01b54971c131ad8d91e5fe3" + }, + { + "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": "5b6f5b31dda72af688b5b359915f71f1" + }, + { + "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": "61b76a0decb6c0f7636a53a80f53376e" + }, + { + "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": "adec754cab077ae6286e56eb2c3e4d97" + }, + { + "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": "d4f1a7991546b0b79da10b5e6b8964b1" + }, + { + "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": "8e586dac4abc9294855ef6d0667a806b" + }, + { + "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": "5a8561f77c83adb62d295970a0840f11" + }, + { + "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": "f295672cec55724618d4916f07d33ae3" + }, + { + "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": "8f05d660c3b4a94b02226ab62630554c" + }, + { + "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": "c9cb02004ee5341124ae5b049d04f7c8" + }, + { + "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": "f1029693d0ae4d969fdd255ca06f7334" + }, + { + "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": "5710ee296fd956cb5585316b2929d19f" + }, + { + "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": "5fd9f53a93308d81924f30f2c7f35a13" + }, + { + "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": "a46ed7ab1ea038c75971f810a3207b07" + }, + { + "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": "5d5039c5c6c02d1239a2ab4e7ac3d5c5" + }, + { + "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": "08203c7da48170eab3947128f3e0e7ec" + }, + { + "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": "7bf6871a254b372852278cb170cc7152" + }, + { + "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": "a1bf89d18b64aa841a42e755ec3f2e97" + }, + { + "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": "91d9f0ae6c6f51857cde4a4495f71dfb" + }, + { + "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": "6f285f929a116a2202575d5cc6700358" + }, + { + "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": "beb5be16857008e54581947ded779993" + }, + { + "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": "933b484ec4ada993895d66ca0f61f9b6" + }, + { + "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": "d0c361b2b27bae042ac9795645ada9d7" + }, + { + "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": "ee5f8ad4e04dfdce19ea99ee80eb5f39" + }, + { + "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": "adbdf11672f0641f5c04b3554cee9594" + }, + { + "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": "43d074b78ce7c4385a3f3459646c664f" + }, + { + "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": "7d436c7ac268d4ffd1d6859e21ac3224" + }, + { + "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": "e7e1fb01d3f7ab5846faae39ba74eea5" + }, + { + "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": "d06204c9526f6f38552206e99f38fb1c" + }, + { + "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": "f5ecfe8dec949d980af8f6d635dd9030" + }, + { + "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": "99fcf0b09696360101c04a2f91827d6c" + }, + { + "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": "21663188e7cef19c1955a053d82b0006" + }, + { + "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": "7fa74f516b691dc1d76552942d810b84" + }, + { + "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": "2e6f999a19a0ce80feeb1f4b1ac0b242" + }, + { + "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": "0ecbe582fc947c200a6c0826d0779f03" + }, + { + "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": "85ae93c087209d6ac7ef2ac93e6379d0" + }, + { + "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": "aec491c3420fc98d04da90a7485a642a" + }, + { + "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": "ca09d034d1d5bfb194db40dd07629463" + }, + { + "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": "9e350b0e6e2cc107bc5816f989c875c8" + }, + { + "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": "10c8b6e51b8fb3e51806dbabd09fea5e" + }, + { + "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": "8a118d6fdb98f111907f278d5f3c54ff" + }, + { + "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": "774ff63b3009edb93f5d0399e8a06451" + }, + { + "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": "0b5316d2273097eb3d8faebadf6e689f" + }, + { + "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": "30e118e6ceeecb13a463a9b681c47c3d" + }, + { + "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": "f97d9ed3e6962e2f0086408b31b8a5d8" + }, + { + "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": "7aeb285b3d1173940179020c1df88cea" + }, + { + "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": "d5c66a99869ae17b2ed1f546b9e24b8a" + }, + { + "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": "69eeb54fa41c38829dc6f938b859cd60" + }, + { + "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": "2911e16971a41fe6257cec4a9f79ceb3" + }, + { + "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": "5cffaaa510259e2b4c86177e02b14ea4" + }, + { + "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": "9c06bf5c650937b2e83f6bce03b0f50a" + }, + { + "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": "e464e2ddbc8635c39c6887ec06e7fed8" + }, + { + "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": "7e1613a5a0a0a2be9baf614e37e7a6fc" + }, + { + "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": "0b09e09d8651f3dfd82344c9488f41bf" + }, + { + "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": "2d75b501cbd8a9a4ceb27511f545a07b" + }, + { + "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": "f3d4f77ed1df93b975c0695d303f6cfa" + }, + { + "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": "66fd5ec9305838ee44aa0d58593373a0" + }, + { + "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": "95f7ef21f996c0557c7c812324ab7f1e" + }, + { + "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": "5a15d4eb02212099df9c6d7b933ed653" + }, + { + "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": "9edcbd93b9c0744631d65a3594ce603c" + }, + { + "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": "754ee6c92eb5244121a59577d250a8f2" + }, + { + "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": "712fbd51d51918eb3562cc167eeeb373" + }, + { + "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": "e6cde066167f770f29b15db824b0bbad" + }, + { + "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": "e9d53950c470d4caf448694fffa4161a" + }, + { + "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": "fe830cb45e2e8614540ae4e2289a9717" + }, + { + "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": "ffb63336fa9bcf26aea5a7851af39c15" + }, + { + "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": "387ac4f621ef2d23dcc59f8ffb1a8db0" + }, + { + "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": "80a9f18a1afe49db0d45c2271d50b91c" + }, + { + "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": "0546a50850d490ab1f3d74f8f2539978" + }, + { + "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": "dfa260ab140f5297c369ad0716d7a073" + }, + { + "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": "16b91714b5191f021d67b3a69fa2b4b6" + }, + { + "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": "9626f2615856f9519c6efd95df30a7b5" + }, + { + "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": "032e48f68af5b2694c938ee54a47c913" + }, + { + "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": "eca3589d1fee9a402a719caae5bba24c" + }, + { + "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": "66621015fc14e5d27247346879bde8f7" + }, + { + "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": "1047d4414bc92e7cecb7c37d78983e09" + }, + { + "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": "8751867dc7e85692692082cab7832dd1" + }, + { + "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": "511bbf7409a6cf864469437d0a8f25cb" + }, + { + "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": "ecab4f347397067d090d612552e870fb" + }, + { + "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": "872dd05f65726d3020dc8aaa9972e0e5" + }, + { + "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": "01ad9626a76941d09ee0e90298e2c58d" + }, + { + "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": "217653fa8db45f3863839bc4f2a481fc" + }, + { + "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": "36ee9e883f50d4f0b9d170381edbfccb" + }, + { + "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": "9a7c65653b3ab679e03ae08d68d0173c" + }, + { + "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": "b0abfa9eb557bc878932ce02b59e5d78" + }, + { + "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": "321e52fb7f11787d0f6f89bb0f2df8bf" + }, + { + "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": "9f1da66df2c9a4a90a96235ef60aca81" + }, + { + "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": "71a01680a8ffffd06162a89d5fd1126a" + }, + { + "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": "4f9ed8340a0cbe290e33ae6d3b229053" + }, + { + "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": "1d994ae3402d82dcd9923d76a8a3220c" + }, + { + "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": "00f6d895638aacc485bb71489b2cee65" + }, + { + "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": "548852fb8bbdf7abb7ac72bf46525b43" + }, + { + "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": "a93abbd7030cf66d6282e13a54317f0a" + }, + { + "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": "793c8f4c45b69ec34ab5d64e5ea92d44" + }, + { + "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": "0ca90d8ad7b4b25ff0f2d842dfee0a21" + }, + { + "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": "6bf1c45cf1b2319a31784a3dee8df616" + }, + { + "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": "e4752e0a8eda01cdf524bf0c41896c95" + }, + { + "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": "22bb56583bb30bc7f5e227ce6fb38dc1" + }, + { + "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": "630d0b1b79fc8a7bd9496b0cc0ab513c" + }, + { + "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": "e05c0c1623af7256b4c25d88083c5096" + }, + { + "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": "53118650ca8e6dad490bbee54a116c4a" + }, + { + "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": "8c688875159a8749a98cea5b0aef13f5" + }, + { + "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": "a0340ab10cb1b353a40bc8e07e9a1dfa" + }, + { + "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": "0959570afe065aa4e8fda29dc334ce91" + }, + { + "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": "8197ffaa7f80701ecd038617e67b4fe7" + }, + { + "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": "cf54534c0fd052dd395d651c11888de3" + }, + { + "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": "674878ba5cafbd72b88b409b638ed8ae" + }, + { + "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": "3af16f0c7cecde6ae716930a6a56524a" + }, + { + "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": "cc87b1ae51400afe734f2f99154bb0f4" + }, + { + "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": "9d7997fb59a2673b75abab20ab165d0a" + }, + { + "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": "9760f81e689e7b1c4e7abec946fd87fa" + }, + { + "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": "9cb21a3105d7c0e02c84ec6de23a8a85" + }, + { + "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": "cde6011b0148cf8373d00f0c4b402482" + }, + { + "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": "55b82ec280c7e709b8bad227ea7e192d" + }, + { + "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": "d2c7b0913bec38b15593ec468dac6e46" + }, + { + "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": "2352704dd6d0b92d9a854d47f73a6757" + }, + { + "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": "4006990df87d891b1b4ca614a72fdffe" + }, + { + "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": "614def14bd669328a6c6be3cebcc0b49" + }, + { + "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": "3733ddddbd61a8f4fd1e734cf131c800" + }, + { + "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": "f2aa893d5127b422748b34d9d6f4e96e" + }, + { + "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": "bd3696e959d11fb0633341782dc99e22" + }, + { + "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": "ec8ad5c0a7e24efd06a8523bd489caed" + }, + { + "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": "7fbfbe3a00f217cea9d88c42134493a8" + }, + { + "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": "f22d82d2a32c1bdae70adb28cfe9f3ca" + }, + { + "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": "e8b11301c86cb038a96e517c3827e60e" + }, + { + "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": "98b07c88aa2fd4aa156e61165c551587" + }, + { + "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": "dc1df9f45b9c4069ba565691a191f506" + }, + { + "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": "e9a4a37b87edfa911f22f7202719eea5" + }, + { + "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": "e3ff1add024f4d9990a871e77de7c564" + }, + { + "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": "a4fa127b4165456e1fb5a994babd79ae" + }, + { + "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": "98eb335baf3035df9ca7579756fdf350" + }, + { + "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": "bc233e4afdc1e5047d38be2a1ff58c87" + }, + { + "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": "2d496db30e5f337d98fd9f5a45514e68" + }, + { + "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": "195728e28567cac968a45830775112ca" + } + ] +} \ 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..b38e1ddf11027517497ab9f0ac1e10df6fc62f7e --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81ad0c20fc49382694a61180871e710ddb84e05f0a718453ab2370d51818c7a0 +size 23511040 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..33fd3dddfe220ad62226c473d4bd1df76eaa7f74 --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2422c3f8f5624bb3e1603a87c3b8e8196127837ae0deefd09aa8c787e2a72594 +size 93978624 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..8bbb85e2a2aee74f4d9794a7991e53414d9a08aa --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d040557bd18eea330e02afc3fea5760378ebfbeb365a7ba51e4cab0038a6ac9 +size 188088320 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..4bfd2c2823b2ec474b1057ff3cf2d56b8a24baf8 --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e03deb92f37b9eafc9f346a6ebe022db783ef59752710c38814b7fb2846dba +size 23511040 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..e77c1237e5eed28d17a4a6082a72b19f63010e6a --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac35b5ede53dbcb7a3a50abaed13e8891df3edcc03cbed73b2966942fb3771d +size 33587200 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..cf16898acbce7ed50d69f9288f3c1b067e7a1ec0 --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f1338d65d19f8abf44ed65ffb19d3ecfdaa5e428023ee9d80e995a3e2a82e3 +size 26869760 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..9206ba190db13efaecc2ed12ecea265effced5b0 --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2799db8d71ec19d93840a794b80987dd4a792bb8b8daf4731b8dfe57a5946f41 +size 93978624 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..9e094e40f0a800f0575d32ef12339170ded4fa26 --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633a87fdc058d86ad352deb5c2c7ec6efc43b7bedcb88744c83824bd17ed1607 +size 31100928 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..23f2fbf3b4da41065fc1159e66cd3d1854c986d3 --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77e6f08b9637dd79814d5c90107508edf688de4ebedc5e64bad9734b8b44ec1 +size 188088320 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..06c45dd8efbd455b5d7b91e8c139bbff182addfc --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a38d5ed76aa8ce49348a5f96e5fd365640475a59bed3c630a274b79e70e863b +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..c8eb7b792f1ede43a5167811ccc03cb3d8f683b6 --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873cbeb8aeaddea29616aeb0a1ee27348eefc6e04723ed3ebf38639d6ac9349d +size 33587200 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..a1767cd595d1f463659b13ea4d67a5de13b0ff4b --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011f3bf70d321d5353efdea00ceabdf42f23d500251f9b3fc3a3b21a764f80fd +size 26869760 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..6cbc1e3d970c166e6590cc1b978836040c851ab2 --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34092749c56002e1c3b997f27d22deb8a63d9a6fc186cdc87853fc0ad5e13343 +size 93978624 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..1c19118d6e3f2cb7fb6067f06f432c562e6d520a --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d0e694a5f525c32c8b1be301bb8a09fec514ed39e4fd54651ce9fc308ce88f6 +size 188088320 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..7363e090df42733b9e170cbd252fb963e80fb7cc --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:054b867f733d7c74a73c384e84d565bd5b39cf34d9afcb63832dc40e16b4e68c +size 23511040 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..e0f0d64cc23f6dac0515421b669fb8ed40975da8 --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4844af6043903f8e87b1a834deaf075af7d882f0b368c2bde8abd3c0e251ecb3 +size 33587200 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..d128dd8bee95c4b0c8ea367a4f96799c39406821 --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54938711969b3da9e7906282fbcc44354c5ccf35466f68f4afd050a9011cb304 +size 31117312 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd479e953ec2853e7690405af45ebe04488aaa02 --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98fa85a89fdc3800fd46e2a9a9dbd5a21af2d07cf8d53351290486cea885c571 +size 31068160 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..b996c6acb61517d2358d8bebbe47fbaeac4fa9f5 --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005bbb2a46e9e2490eb633af43a8b612e5caf5b8e7cd3721a649bb9ffcd41c4f +size 93978624 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..4ccf390feb1298ac5a16ae9bf2f06312fd5d9918 --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55813529e04906a72660dc5205004c1cc50885c7feca5aa2bae7fc23ddf11e01 +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..09c78d31581956c0b0aa14e1211ac9b1a239b4bb --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a644b678d1f537310478c8bb9e747cda8e3bfb9b5595140ab3e8c42e76648b0 +size 23511040 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..1880cedef167c5eb43f4d3408cc6718392f04d71 --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9289570df37db7d8f04ab388c88dd42c4e3253c13105cb241a1194d14e8d58d +size 33587200 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..607cc73d585206063c67cd9551289076fa02f4dd --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92925b4953b951a7844e7805ecadaf9f681c4fd773d4033a520a62251f85d49e +size 26869760 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..43c2e64a95bd86514da49c4b1c2a05fa3d052b95 --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:631323eab1a60b6f7b501f8dd3bf72dafcdf7b6b9f26211d0f66c3a14edd3ab4 +size 188088320 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..567e1c5fc6abb29e1bdcdde7757a5aa6fde0e39b --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae538a8e281455f805a5b88a42d94d20fb7a9daa02786cd139b85ad3f2dd9f33 +size 23511040 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c11cc41d9842365f788fa3cf5628e02ab0286e5 --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7208b13dd217e5315a190a7b1c703a8a748f778ce522b17df98148a6142bf931 +size 33587200 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..c3025876a87a49b4ae0abf6d4a16f032d648d854 --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32bb93010998af0d94710a59074aa89ac6bcd6144dc96450668cd1fda0333058 +size 26869760 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..3c6fa047acaf54fd9e5c7ad4e77cd273b2c48f14 --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a3d82d05afdd4376df6151a92d67b99794702651d5d24e5d7ecb8db8a2480f +size 93978624 diff --git a/params_shard_128.bin b/params_shard_128.bin new file mode 100644 index 0000000000000000000000000000000000000000..4bcd814fca0e0c9a31edfb4d1dda8b4518b18cc8 --- /dev/null +++ b/params_shard_128.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b0a15d17893cc763123866997f7b6d11ff072ece0ad526115f8ef99b6f3508d +size 30269440 diff --git a/params_shard_129.bin b/params_shard_129.bin new file mode 100644 index 0000000000000000000000000000000000000000..ee9b4efdcbbb5140507802868a032deb6b35c4b1 --- /dev/null +++ b/params_shard_129.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e478a86521c1467c647a77c947ccc80a2f2a34017accfcbb6724e7f1f591c16f +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..1200a94b82665b95dbd6f146a489016d75abe443 --- /dev/null +++ b/params_shard_130.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8a5decb24ecafe476bc202b85a16c7f060c5eb31bf2fa62985a41ceb84d3a9 +size 188088320 diff --git a/params_shard_131.bin b/params_shard_131.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc1209e4b5b60f50424703be91c6f8056c6d3859 --- /dev/null +++ b/params_shard_131.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ed3e57be5508e7d12632be82bf424807c789ff7538b5cce1778122b722c3da6 +size 23511040 diff --git a/params_shard_132.bin b/params_shard_132.bin new file mode 100644 index 0000000000000000000000000000000000000000..508498eadb3c537e38dd012261981d72bbb9ac99 --- /dev/null +++ b/params_shard_132.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea54d252c7626926abd02e57c333fcc799ab9c7182f2293b817f3157b997b0d9 +size 33587200 diff --git a/params_shard_133.bin b/params_shard_133.bin new file mode 100644 index 0000000000000000000000000000000000000000..e4c0019b063016958b1e27c0bd22415a9edf7395 --- /dev/null +++ b/params_shard_133.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179f201816bb9613da2cac46ea7f1e130a7c3d7eac4217cff19c65b3431b3f10 +size 26869760 diff --git a/params_shard_134.bin b/params_shard_134.bin new file mode 100644 index 0000000000000000000000000000000000000000..29816752c7908062ab920144de6bb2f2e1feaf60 --- /dev/null +++ b/params_shard_134.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:547cfc54eab6429f686ce750971c1f1d6a40a38a40019499fe348bf0c4614bd6 +size 93978624 diff --git a/params_shard_135.bin b/params_shard_135.bin new file mode 100644 index 0000000000000000000000000000000000000000..c14a0da78d880ca2c34f0f7ace5d43abcabec8f8 --- /dev/null +++ b/params_shard_135.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1850a376c03def335e63532e74d3beabee7204c7f36ee45eb5853f7e9790fd45 +size 31117312 diff --git a/params_shard_136.bin b/params_shard_136.bin new file mode 100644 index 0000000000000000000000000000000000000000..c05d0109b74feb697d076d59643ab9b31bce33ac --- /dev/null +++ b/params_shard_136.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c879e8479e98feaeabc525ec2ecfd4a05520a4ec731f0c601c138de0ebeddc3c +size 188088320 diff --git a/params_shard_137.bin b/params_shard_137.bin new file mode 100644 index 0000000000000000000000000000000000000000..2bd0e5a19eb8a59224274054d4aec6cfdb54d28c --- /dev/null +++ b/params_shard_137.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a8f32bc35aae1aebb0ba684a20867dc9b6d3e630755318317a51f285339d83 +size 23511040 diff --git a/params_shard_138.bin b/params_shard_138.bin new file mode 100644 index 0000000000000000000000000000000000000000..6c3b7a5d58cfa53f7eae6e3d31c7ba0f5579db07 --- /dev/null +++ b/params_shard_138.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c9c1fe1828d4638358b763ce20deb7fe9ba978b3aa3e0da73e1fb0418b499c +size 33587200 diff --git a/params_shard_139.bin b/params_shard_139.bin new file mode 100644 index 0000000000000000000000000000000000000000..2dd60f5d4e6d28b954df547757d50fcd24db425a --- /dev/null +++ b/params_shard_139.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:749758fc78ca4edc57c3a069736de7890c0712c8ebc22d8677857764b61e51cc +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..ffb1a2661d4098d76f98cb494aec306cfa0f8504 --- /dev/null +++ b/params_shard_140.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff31e255f8a8d94ed4b6226b8bb9c4837258748d4dc307b955bc7b635cc3d21 +size 33587200 diff --git a/params_shard_141.bin b/params_shard_141.bin new file mode 100644 index 0000000000000000000000000000000000000000..6f05d9453983eecd9327f4fcc62feecedf3356bc --- /dev/null +++ b/params_shard_141.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:769bcf889dcf36b40b0afbd742675e6c0ca1a86bd90140ad9c3f8e8bdb2c4d9e +size 26869760 diff --git a/params_shard_142.bin b/params_shard_142.bin new file mode 100644 index 0000000000000000000000000000000000000000..d4a59adea9474713b79c6f05b40677caad935e4b --- /dev/null +++ b/params_shard_142.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adf58f6067177707b569c68a2e00e9bf998f29b2a75affe06c8101541de5b20 +size 93978624 diff --git a/params_shard_143.bin b/params_shard_143.bin new file mode 100644 index 0000000000000000000000000000000000000000..9afff09857aa42f4afcd14e5d65fae1576708cf1 --- /dev/null +++ b/params_shard_143.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13dd34574a4a9eca918c2bc418b132fc7604dbdc95ef3fecbe90faa4c2b314cb +size 26894336 diff --git a/params_shard_144.bin b/params_shard_144.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc26f372f673c603ac40705bf9737bd075e444e2 --- /dev/null +++ b/params_shard_144.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b581d1b69450488d58a02a5ca915a3226bc45a14d0401f708a732af5e171cbc +size 188088320 diff --git a/params_shard_145.bin b/params_shard_145.bin new file mode 100644 index 0000000000000000000000000000000000000000..39ec827a216ea4e7336bfdbba97864c6258ae88f --- /dev/null +++ b/params_shard_145.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83436ba2df99be3b6178c8f0ae6864b0717aec406bc8a9e9bf1a4b908e9a1c7 +size 23511040 diff --git a/params_shard_146.bin b/params_shard_146.bin new file mode 100644 index 0000000000000000000000000000000000000000..037cb9a6aab1b1109fb5ffc8790b67c63fd0b2ab --- /dev/null +++ b/params_shard_146.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a132d03ae871d10aaaae047bd6bbc0da73f3e7bd13e42decd6d0276e6c4567e2 +size 93978624 diff --git a/params_shard_147.bin b/params_shard_147.bin new file mode 100644 index 0000000000000000000000000000000000000000..85f4e0c3bd3f8ed83af23d6bca8fdfef92c937ad --- /dev/null +++ b/params_shard_147.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f830cbd09b47209e5e9ceac40bfcbf648f4fe9c85bf57144582aef34c8ee9a +size 188088320 diff --git a/params_shard_148.bin b/params_shard_148.bin new file mode 100644 index 0000000000000000000000000000000000000000..361a9172af73d7720d89b5377d29ab3c590265ff --- /dev/null +++ b/params_shard_148.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c369452fe1e1b6a8ad559e5d06c887709748f6293dfde9f484f2efe37d9643a +size 23511040 diff --git a/params_shard_149.bin b/params_shard_149.bin new file mode 100644 index 0000000000000000000000000000000000000000..8aacfe10408c6962b1ffb4e1024030b50d2da773 --- /dev/null +++ b/params_shard_149.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be42935d002d64b660458bb9ce92db0b6de7b188d3b7dd43de0f7fa4c31de1cc +size 33587200 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..76ec1b09a8ad70a53c5fdcdb4eb8c223d1f80b6c --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4999922756cfca4ec1dbadf0d0be999a0216fef04feaf2d384492fa2b3b1a6ea +size 31117312 diff --git a/params_shard_150.bin b/params_shard_150.bin new file mode 100644 index 0000000000000000000000000000000000000000..9bd7afc19b1288014483cadaa5778be991bc0c4d --- /dev/null +++ b/params_shard_150.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50380decb2d5a052e5ce56716daccb995c57a684d62f9d1cef71f024ac013656 +size 26869760 diff --git a/params_shard_151.bin b/params_shard_151.bin new file mode 100644 index 0000000000000000000000000000000000000000..f3767cf2c4271e253a274b07d98a68d3a981cbec --- /dev/null +++ b/params_shard_151.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1f54d756722db3af9fddbc6744ad37b55849ca4d71ab3e5872539c7c942b095 +size 93978624 diff --git a/params_shard_152.bin b/params_shard_152.bin new file mode 100644 index 0000000000000000000000000000000000000000..e68ebe216ef86aed09ca9fea8ae44a5ca16d16f3 --- /dev/null +++ b/params_shard_152.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e802d97305a2142730319c94b0409071bc5f304a8dbd1a65d068dd242c6efb +size 31100928 diff --git a/params_shard_153.bin b/params_shard_153.bin new file mode 100644 index 0000000000000000000000000000000000000000..20382e3b36ab1acff05755c2e1e05a7979740ebd --- /dev/null +++ b/params_shard_153.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d23b43ff76a7737be3dac25db8779145a1643fea623ccf068d352ffbec9a83 +size 188088320 diff --git a/params_shard_154.bin b/params_shard_154.bin new file mode 100644 index 0000000000000000000000000000000000000000..548747649a4daf7b4d45735cb6b94e23dede9847 --- /dev/null +++ b/params_shard_154.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce53feed326f3047d6b431ab9eb3be7ca8004495e3ec013b2d0e937c357a9dd +size 23511040 diff --git a/params_shard_155.bin b/params_shard_155.bin new file mode 100644 index 0000000000000000000000000000000000000000..cf0d38efc8ef41449113c7c6e04cfb0456731d00 --- /dev/null +++ b/params_shard_155.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c06294b4753bcad1b406028fabcf608763e85c8a12ef0f43027ef30ca774a40 +size 33587200 diff --git a/params_shard_156.bin b/params_shard_156.bin new file mode 100644 index 0000000000000000000000000000000000000000..e812808a20c9016b873d0c9c3eab3d9a27b18729 --- /dev/null +++ b/params_shard_156.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f1f260edb73f5ff5b8aff870972c54383ac23c1da56cab99aadbb2f6c178604 +size 26869760 diff --git a/params_shard_157.bin b/params_shard_157.bin new file mode 100644 index 0000000000000000000000000000000000000000..1630f7b70fcd5150c67e242f5451f809db601df5 --- /dev/null +++ b/params_shard_157.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfa99c345e3a9d528f86f0182e9dec27a7d859b0f6dbb979264944ced7d1d25 +size 93978624 diff --git a/params_shard_158.bin b/params_shard_158.bin new file mode 100644 index 0000000000000000000000000000000000000000..6853faf228119028c63e509427b705e66e80aa7b --- /dev/null +++ b/params_shard_158.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1b05323c3bc24e73b7dc8f60bd681d392bc1162c10bbb60a82e8c6240ff478 +size 188088320 diff --git a/params_shard_159.bin b/params_shard_159.bin new file mode 100644 index 0000000000000000000000000000000000000000..374bd42cf3577a58c760f6cad8de81379a031eab --- /dev/null +++ b/params_shard_159.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3605f3e50b2506ab761afaad911973a60e5e5189f7d302d871d1a97cc0c552 +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..7b65c0643ee9fe72a0dff4c586c1c4b18007d230 --- /dev/null +++ b/params_shard_160.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3156f5b0d7a201d0b21d3f62effba4fbbc168d43ef3afd7d31ad8b2d69905bab +size 33587200 diff --git a/params_shard_161.bin b/params_shard_161.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e2f762619173e667b990ac704fae53c1286fa75 --- /dev/null +++ b/params_shard_161.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af5c33b259fe7589ed28c8cfbf51900efa2d04efbc8c338ae87d6e9edd06ddb +size 31117312 diff --git a/params_shard_162.bin b/params_shard_162.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e689d5ad4ae6e1fb3f9536c6b7c7245265b21b0 --- /dev/null +++ b/params_shard_162.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0467558dfffc6b39471183e8ba0768a142e6d119b8433bbaadb633abe9b491e +size 31068160 diff --git a/params_shard_163.bin b/params_shard_163.bin new file mode 100644 index 0000000000000000000000000000000000000000..11773c2e6b7162ff3d86878bacd46e663fb808fd --- /dev/null +++ b/params_shard_163.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b8d4eaa37b60795acaa2fdeafd8f95721aeeda942f5e71c604116ae5883115 +size 93978624 diff --git a/params_shard_164.bin b/params_shard_164.bin new file mode 100644 index 0000000000000000000000000000000000000000..e157f0ae0a0ea8d88696caf20dc89a295968531e --- /dev/null +++ b/params_shard_164.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c93ca72ffd6df8a1b38d7ce8641d5fdc8dbe423e67ec2724c6b201ad1f450b +size 188088320 diff --git a/params_shard_165.bin b/params_shard_165.bin new file mode 100644 index 0000000000000000000000000000000000000000..99e1a1e99bde406d95023c821f629c626e3656c6 --- /dev/null +++ b/params_shard_165.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6036dbd4a6e47b58dd18cd07d096addc38c8e723816eb84fe5bf3bb816a3d6e3 +size 23511040 diff --git a/params_shard_166.bin b/params_shard_166.bin new file mode 100644 index 0000000000000000000000000000000000000000..2326d35a6c33acaba475cb5381a7dd1c4e6cfccf --- /dev/null +++ b/params_shard_166.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363a3aacf6a4350cc177efdb41d4acec4605575833c3339e9e31f7db891a705c +size 33587200 diff --git a/params_shard_167.bin b/params_shard_167.bin new file mode 100644 index 0000000000000000000000000000000000000000..a27fc14ec2dbfadcb9f98c7c4f6ee1c41a17c0ac --- /dev/null +++ b/params_shard_167.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed09e193c4c77434312898d2fa9b7cfc55bfc6f101c30459b9969fad81a3ec39 +size 26869760 diff --git a/params_shard_168.bin b/params_shard_168.bin new file mode 100644 index 0000000000000000000000000000000000000000..e2bc047df358b6bed821eb09f3105035a0db2bf9 --- /dev/null +++ b/params_shard_168.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc884e7743423b69d9cc46e4489c3f24421ef165d920ea33f6646c8c2a11e8e6 +size 188088320 diff --git a/params_shard_169.bin b/params_shard_169.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c9ac97d5ffc9c31182ab381ec113651f382f9df --- /dev/null +++ b/params_shard_169.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f4660199b0e064585820bd3d12e4b2d373b5cee3638060775559b3456488db +size 23511040 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f674b67db93721c43a85d933977087991ac71b9 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd5dc98572b0f380ec7a6394dd698ef9fa352b547b31ddbe4e4ed02927625f9 +size 188088320 diff --git a/params_shard_170.bin b/params_shard_170.bin new file mode 100644 index 0000000000000000000000000000000000000000..02b2efc9e41c65b8662d64d45dadacbb2d161487 --- /dev/null +++ b/params_shard_170.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5fd2781b2d4cfa5dc71577744e1dc482876f68f8fe7830630b70e49ccfcf5b +size 33587200 diff --git a/params_shard_171.bin b/params_shard_171.bin new file mode 100644 index 0000000000000000000000000000000000000000..642f8a4aa13bf6d4cc040f9ec6acc592e3057e2c --- /dev/null +++ b/params_shard_171.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a417616447e0d8968dce2ee31cb800ccd0a506f62c42b4500a9f4164dbbc835 +size 26869760 diff --git a/params_shard_172.bin b/params_shard_172.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e93675f6dea51340bfe5ed215c47a8afadb6155 --- /dev/null +++ b/params_shard_172.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856f58b6537a960c45e61e0478c4ccafb9b40255ff5b910288eae9203aebb848 +size 93978624 diff --git a/params_shard_173.bin b/params_shard_173.bin new file mode 100644 index 0000000000000000000000000000000000000000..9a70684ad373a9c87674613618516b6735dedd3f --- /dev/null +++ b/params_shard_173.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb0733e64cf3627eeffedbc0be2085efe9214adeb3de8b15972603f42412dd0 +size 30269440 diff --git a/params_shard_174.bin b/params_shard_174.bin new file mode 100644 index 0000000000000000000000000000000000000000..ceddbb27331a3a8bedd93e077d8e2b0edca4306f --- /dev/null +++ b/params_shard_174.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bd867a02f7d00950069a4dc9ffddae32d8e990d7b7020c322ad235d0b23d73b +size 93978624 diff --git a/params_shard_175.bin b/params_shard_175.bin new file mode 100644 index 0000000000000000000000000000000000000000..2953042ef683d4853d016399f71e7ba24985485e --- /dev/null +++ b/params_shard_175.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8939c4fa83ff6f2b354dc575ff38b86bf64e2ef77f205f670704ff726fd938cb +size 188088320 diff --git a/params_shard_176.bin b/params_shard_176.bin new file mode 100644 index 0000000000000000000000000000000000000000..d39a6cd6d42c1ef770e0aa2a6bb0c76c72f2081a --- /dev/null +++ b/params_shard_176.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff7103f492319f9c06f58b0cc2fb4ed34e7624117df01780cf11ae25bb68bb0e +size 23511040 diff --git a/params_shard_177.bin b/params_shard_177.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ff3b2bc0e517ed32036bb515fb65442ee4ec390 --- /dev/null +++ b/params_shard_177.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d75229e11fdead48296b082404b6fce31297580a0294a70000301ec1d6aabf1d +size 33587200 diff --git a/params_shard_178.bin b/params_shard_178.bin new file mode 100644 index 0000000000000000000000000000000000000000..b568bc95ebb821ff1e22f55d194eb8c04c73e5e3 --- /dev/null +++ b/params_shard_178.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcecf28cde5c6b2cf6f14a7df48520f320bb3f4c4a0672fd203b5588696a6294 +size 26869760 diff --git a/params_shard_179.bin b/params_shard_179.bin new file mode 100644 index 0000000000000000000000000000000000000000..2b1bb71c6db050a68a7e17c935d763986cb2d35c --- /dev/null +++ b/params_shard_179.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9ef0bbf6f8829e9e63b78cd5684943f2355dd022f3d4f0338830ab96ebae106 +size 93978624 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..9c2a226d44b4143e24f5bc397f02102fb223bac1 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c49fa1166071e9a21d2f76892a87987824ca956176e734939ee24b77d692b7b0 +size 33587200 diff --git a/params_shard_180.bin b/params_shard_180.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f3bc55577ca00427db549f61d466d58b76d17f7 --- /dev/null +++ b/params_shard_180.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5dd5af389506ac4b4e39f58e7b11f54f1dce2d6b3e7406e678ae63857479cdb +size 31117312 diff --git a/params_shard_181.bin b/params_shard_181.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa12230b61c2d2d40adc4b93ae091379c3ebe16c --- /dev/null +++ b/params_shard_181.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bfc103aa3466c7431cdc1562f62e2e30b47dec681a0aceaa6b73a21748d56b6 +size 188088320 diff --git a/params_shard_182.bin b/params_shard_182.bin new file mode 100644 index 0000000000000000000000000000000000000000..7436898342eb65276f7b35ca82c0f56ebeaff991 --- /dev/null +++ b/params_shard_182.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0997e8eea570f524ba7896364d72ec54ebfbb1cd61e6b6a74022baa29e4897c9 +size 23511040 diff --git a/params_shard_183.bin b/params_shard_183.bin new file mode 100644 index 0000000000000000000000000000000000000000..f54d160090f523d0a127bbd2248bd8b3a9c62831 --- /dev/null +++ b/params_shard_183.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e7c98e5b93143c09f18f9d7fc4d6a030e9509d8687014246e7d31728f30da7 +size 33587200 diff --git a/params_shard_184.bin b/params_shard_184.bin new file mode 100644 index 0000000000000000000000000000000000000000..97a5efd5834576b009da1a23d3f621430f55b39d --- /dev/null +++ b/params_shard_184.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a69903e08f34b29e3eddd3fac248f2681c4e590d56fc278329103ebd475c2161 +size 26869760 diff --git a/params_shard_185.bin b/params_shard_185.bin new file mode 100644 index 0000000000000000000000000000000000000000..f62e62fc4c611568318ad64ba30ec8bfd9b6725a --- /dev/null +++ b/params_shard_185.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96849fcce277c52f6b32afe227a75229201c07e85652cd7819a32e81333e1396 +size 33587200 diff --git a/params_shard_186.bin b/params_shard_186.bin new file mode 100644 index 0000000000000000000000000000000000000000..77c0f0f33e7e310edbb05d80ee37ec94264dbf0b --- /dev/null +++ b/params_shard_186.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2a91312de44d8956804c2619628b7dc651ec210ffed218d511396d4a9df141 +size 26869760 diff --git a/params_shard_187.bin b/params_shard_187.bin new file mode 100644 index 0000000000000000000000000000000000000000..0cf7129c5ccc8f52a5dfc43c10c2dd1b91198eb1 --- /dev/null +++ b/params_shard_187.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:035730d2a6a7006efa901f5399e1dccf874b47c238ebf9e426863a5d03ae0bdd +size 93978624 diff --git a/params_shard_188.bin b/params_shard_188.bin new file mode 100644 index 0000000000000000000000000000000000000000..71e0b57e1c92a50b97db01911a058702ee972583 --- /dev/null +++ b/params_shard_188.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c98b3679614011759a229e5ff8f8455cb64e646cc87b95adc7ad444f910d0e7 +size 26894336 diff --git a/params_shard_189.bin b/params_shard_189.bin new file mode 100644 index 0000000000000000000000000000000000000000..99c8602e4c93665e7643ae6a93f0b1fd4f7ea0dc --- /dev/null +++ b/params_shard_189.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0427ff5b39b3f057f9bdddda10ab55f8b0c0c03d726a824b680220b646c00940 +size 188088320 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..6572d5067ce9c2f9c1270fe36578e60bf85b1672 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:911a9584bcb529b68b93d9818364d3900fb13c2f87c453f8eeee0f2cdc1c5973 +size 26869760 diff --git a/params_shard_190.bin b/params_shard_190.bin new file mode 100644 index 0000000000000000000000000000000000000000..f928d2f67ba895767afde40e63e59118accbc562 --- /dev/null +++ b/params_shard_190.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a2fa2ba7311220fe00c2750ef7f53660af317eed74b86b9a25bfac2232da77 +size 23511040 diff --git a/params_shard_191.bin b/params_shard_191.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0f6d139552c3ad46f0e087d160824b82374bed2 --- /dev/null +++ b/params_shard_191.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04c8a55c66bd085dbfb79c2ca6821e0281a7d0a5863432d83390594793df3b1b +size 93978624 diff --git a/params_shard_192.bin b/params_shard_192.bin new file mode 100644 index 0000000000000000000000000000000000000000..3053447a39fa00c484fa914232d01499bf6791c9 --- /dev/null +++ b/params_shard_192.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c92f38bfae61cdd13a9263ee64573a1794c76390977c4c4d12407d5790613a4 +size 188088320 diff --git a/params_shard_193.bin b/params_shard_193.bin new file mode 100644 index 0000000000000000000000000000000000000000..c3f9ec247fa35b93d8c36351171bcda91c5261da --- /dev/null +++ b/params_shard_193.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1eb4615d9e1f7ca430cbc100a4b8f554be7571c579d463e2de69f37571bcc21 +size 23511040 diff --git a/params_shard_194.bin b/params_shard_194.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e3e6dd6e583f967c1e790552b52d78835f485c9 --- /dev/null +++ b/params_shard_194.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e847b745b28effb15dc95b66c17ffb9e00195d1d045345bde2340b565e9b0d3 +size 33587200 diff --git a/params_shard_195.bin b/params_shard_195.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0e2610a7df598d8e022ce8649fbce334ae0d8e4 --- /dev/null +++ b/params_shard_195.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4392441271426551cf62f48b51b31e8ec4a4869745043c4eec719f26eea0fa +size 26869760 diff --git a/params_shard_196.bin b/params_shard_196.bin new file mode 100644 index 0000000000000000000000000000000000000000..8abe5cd551b3ab5a9cd2ba145a76a75b34ff0289 --- /dev/null +++ b/params_shard_196.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884a2bdfd6cbc73a7d7193e531ab64d657768d8d992dc0ad43f2e9edc076eb64 +size 93978624 diff --git a/params_shard_197.bin b/params_shard_197.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac2fde3e87c6e1f817666ecf21df78557b3a06ad --- /dev/null +++ b/params_shard_197.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10681d994afcbbaf661935beeae52f834d595670b8455e5ee3da0397e45e131f +size 31100928 diff --git a/params_shard_198.bin b/params_shard_198.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f01dd78e685acee40ba1ab91abbb1f0fd4d90ff --- /dev/null +++ b/params_shard_198.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd9118af106d379c879feb7f8c0d1e86dde7cb137f8941418349b7cfd6ccc5c +size 188088320 diff --git a/params_shard_199.bin b/params_shard_199.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ce0c8e205976923298d1d6cb4d6441fd0874cb5 --- /dev/null +++ b/params_shard_199.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3bf20d91c937619578729033efb39e05cd2d9130c14dbda8aaa937664469d4 +size 23511040 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..e99454c0565049fb2538f90b3d70e3841d7e1df5 --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13772f68b7e4d3ff4c44caf1d1541943a7a54b313a2dbd89f04931d15edfd4cf +size 188088320 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..be7413f250e0060e2d12fce6c08c17a30e5eefe5 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5421770f8e10de68c90c1e0a049940d8946ed1a2004e6bd2fd30ffce7a0fc7 +size 31068160 diff --git a/params_shard_200.bin b/params_shard_200.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbd5c583508d9b92d6fae23e116a73a23d57f47f --- /dev/null +++ b/params_shard_200.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:686808c82fc644680a53d876204d6002c943d0e33158f07cd1fe5121509aa178 +size 33587200 diff --git a/params_shard_201.bin b/params_shard_201.bin new file mode 100644 index 0000000000000000000000000000000000000000..c57d8a44d807454846f24d8ae121e6760a1baa64 --- /dev/null +++ b/params_shard_201.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70658a65b177337a3bdc3c0e8ed7b946c67a43eda94d31389ffcba33f54bbbf1 +size 26869760 diff --git a/params_shard_202.bin b/params_shard_202.bin new file mode 100644 index 0000000000000000000000000000000000000000..d050888c4f99a88f8debd689f8a064f138df1e17 --- /dev/null +++ b/params_shard_202.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae4d9fe73d64aa41318660951dfd4ae3a6b1bc7396b36c30b64c3de7bad3433 +size 93978624 diff --git a/params_shard_203.bin b/params_shard_203.bin new file mode 100644 index 0000000000000000000000000000000000000000..940af5e3c80e0a42a44879cb7db6e9feb7e43d1c --- /dev/null +++ b/params_shard_203.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3973f3d97937c72151a3718bc39da0eef549aef90039c599f6dbaecf8595c34 +size 188088320 diff --git a/params_shard_204.bin b/params_shard_204.bin new file mode 100644 index 0000000000000000000000000000000000000000..b3d6ecf47d2fb39627ff88dc8227b64e9a4a7a58 --- /dev/null +++ b/params_shard_204.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96c38972567a29253b5dd34c30ff5bdab3c1ea3b058e42f5d06546f5b4f3281 +size 23511040 diff --git a/params_shard_205.bin b/params_shard_205.bin new file mode 100644 index 0000000000000000000000000000000000000000..e25a68c5cd59529afaa3005f3340df440534b928 --- /dev/null +++ b/params_shard_205.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ada1fafd7ea32e2aa7a32d0c4b254c85326145ae7998c28531eb64f51a7d4d9 +size 33587200 diff --git a/params_shard_206.bin b/params_shard_206.bin new file mode 100644 index 0000000000000000000000000000000000000000..e04bbff531794dcc030ecc07a5bba9e0aa4ce42b --- /dev/null +++ b/params_shard_206.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d540158a9dfb62922b5f2c8d6e38706f3043661e3636af374be9f0ac19c23c8 +size 31117312 diff --git a/params_shard_207.bin b/params_shard_207.bin new file mode 100644 index 0000000000000000000000000000000000000000..aefdbfd5e1f02e6e700e2df8b5fe950abd5f3824 --- /dev/null +++ b/params_shard_207.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0bc3d65c9130ab17e9a8077de47f635eef426e017fbbafc6178e0ae57e3e85c +size 31068160 diff --git a/params_shard_208.bin b/params_shard_208.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ac5fca48c6e55cebdf02844986f202914989a14 --- /dev/null +++ b/params_shard_208.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97a8b4047c2e49766baf763e1fcc45e0c8aa8a4ed4a4f88c0e4df491fd05b74 +size 93978624 diff --git a/params_shard_209.bin b/params_shard_209.bin new file mode 100644 index 0000000000000000000000000000000000000000..17440bea3aa52e6c5a151a24b5c3c1712ffda331 --- /dev/null +++ b/params_shard_209.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e669b5b410a0249030a97f5ee96faf078ca3aa4d2a4cb365b1ec056fed7ea6e +size 188088320 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..fd078ba9cedcd9d74da268660de55400d6815d05 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7cf9b5898ee03b977c8f8b3dfae401588f9030ae9347dc92f2f5b0fd17bbe51 +size 93978624 diff --git a/params_shard_210.bin b/params_shard_210.bin new file mode 100644 index 0000000000000000000000000000000000000000..f96dc8ca16ad59b338642072e7830552d56f8078 --- /dev/null +++ b/params_shard_210.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b65e29c6e0f315246f35b5c1b9f3c52d38373e05d281beb1d85ab68fa311168 +size 23511040 diff --git a/params_shard_211.bin b/params_shard_211.bin new file mode 100644 index 0000000000000000000000000000000000000000..471b60b76354bda4776e199a009a517c77dee5d3 --- /dev/null +++ b/params_shard_211.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c32e9acadb14287900e380556cab6f14eb64badb3e83c18854f2a58a28601bc +size 33587200 diff --git a/params_shard_212.bin b/params_shard_212.bin new file mode 100644 index 0000000000000000000000000000000000000000..cb57f240948c58c3a869eb12b4b90264002dc01d --- /dev/null +++ b/params_shard_212.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba5103dafd8596f0930a747c13dc4a0898cabb8cff487701d1534b48feedd18c +size 26869760 diff --git a/params_shard_213.bin b/params_shard_213.bin new file mode 100644 index 0000000000000000000000000000000000000000..6f66b7abc39095931e306d3517dd6b964a265f8e --- /dev/null +++ b/params_shard_213.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9082399df672a54cbf1e0c062ed741aba2cd5e6d2a6b67f4ddc314a17172b514 +size 188088320 diff --git a/params_shard_214.bin b/params_shard_214.bin new file mode 100644 index 0000000000000000000000000000000000000000..75e74973fa0858fc79e1771f6e4a85d2cd82b0c2 --- /dev/null +++ b/params_shard_214.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e05bc8be11bbdb026d5b62c6bce311a0e49040474a303df8541fb8cb1bf1573 +size 23511040 diff --git a/params_shard_215.bin b/params_shard_215.bin new file mode 100644 index 0000000000000000000000000000000000000000..ade7b1288e990bbaedc0754cca185b35e4d9a840 --- /dev/null +++ b/params_shard_215.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6732986e19c953ab48176dff3d711358cad3064f642357ef183afa47ebbd90f9 +size 33587200 diff --git a/params_shard_216.bin b/params_shard_216.bin new file mode 100644 index 0000000000000000000000000000000000000000..8cd2e2b00d2f5d7e630b131c2a2505f9c75f2f1e --- /dev/null +++ b/params_shard_216.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7efee9f1bb427b9727e5a00ae223d4bc53c760b0d6a97df15f1d6862841b76e +size 26869760 diff --git a/params_shard_217.bin b/params_shard_217.bin new file mode 100644 index 0000000000000000000000000000000000000000..225fbe9f630ca446134404975f47402431e46d61 --- /dev/null +++ b/params_shard_217.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfbd060be1a50f336fc8c533e404756023ebe530dddb75a7965632be8ddf8715 +size 93978624 diff --git a/params_shard_218.bin b/params_shard_218.bin new file mode 100644 index 0000000000000000000000000000000000000000..102fb30631a2d009cc5755fc3a95d50c6e46e2a5 --- /dev/null +++ b/params_shard_218.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0bbdee9dc1b41bd6075238f340b123df9f6df04e7c96349d8a8266cc229ec67 +size 30269440 diff --git a/params_shard_219.bin b/params_shard_219.bin new file mode 100644 index 0000000000000000000000000000000000000000..0c026b41b905e4b30bf66c1ae4f465b77e26542e --- /dev/null +++ b/params_shard_219.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c274793ac2cbf38ba0f3b1d8206194a23251bf635ca80bce85b35c78bd41b202 +size 188088320 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..b579aef9294058ddfb36fe65f633e870a4b6f053 --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be5afbe78c657d9285ca0b935a219b594df2bedcc2640d33941dce679b507025 +size 93978624 diff --git a/params_shard_220.bin b/params_shard_220.bin new file mode 100644 index 0000000000000000000000000000000000000000..98409813d133a904b727c7a13e5235949a2608c3 --- /dev/null +++ b/params_shard_220.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31417a45fecf9e1de0b5de881f75eb5a2be388f42ed06ab34a736c023419068 +size 23511040 diff --git a/params_shard_221.bin b/params_shard_221.bin new file mode 100644 index 0000000000000000000000000000000000000000..b60f07f49de191f7f066cb16bbfea87371d6d1de --- /dev/null +++ b/params_shard_221.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f437bb9ae57e4fcf40d68dd5293c467b1ba85840a84abb8bb8b405c7d6d7a05 +size 93978624 diff --git a/params_shard_222.bin b/params_shard_222.bin new file mode 100644 index 0000000000000000000000000000000000000000..9974c75c2e9ef3b889210a410acc8c4f7fcee645 --- /dev/null +++ b/params_shard_222.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b84846e241f1976b9b14eeb2b0b843b9ec9246c3ec873faebf45fb358823a72 +size 188088320 diff --git a/params_shard_223.bin b/params_shard_223.bin new file mode 100644 index 0000000000000000000000000000000000000000..486eaab7ac57cc0c7acd8e02813687abdf8a3eda --- /dev/null +++ b/params_shard_223.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6044a67a7f1c249da42082d4dca0262619d871e28977569521d44817a0cf81f0 +size 23511040 diff --git a/params_shard_224.bin b/params_shard_224.bin new file mode 100644 index 0000000000000000000000000000000000000000..57a8532d41d188fe92121a6c5d096f884cb9465d --- /dev/null +++ b/params_shard_224.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d304b15609a428c4db6aeb8f859b98d3b56a6e8049c827ec29e66e29c7f1414 +size 33587200 diff --git a/params_shard_225.bin b/params_shard_225.bin new file mode 100644 index 0000000000000000000000000000000000000000..63a7c4b43b1ce7d57a14ebd52d9865fab89f9a92 --- /dev/null +++ b/params_shard_225.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c11559302b34108779933f1d9400bc626e0077d1c952543bbc4c0d0428fc3299 +size 26869760 diff --git a/params_shard_226.bin b/params_shard_226.bin new file mode 100644 index 0000000000000000000000000000000000000000..c5b618f996e559d3254118bcb42b1c1371990dda --- /dev/null +++ b/params_shard_226.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:078366d6be7d80fc8184d2b5a3465d41709671053356f3950123a547b256c37d +size 93978624 diff --git a/params_shard_227.bin b/params_shard_227.bin new file mode 100644 index 0000000000000000000000000000000000000000..b3e297a96586305f644d1d7587e4fd11cea6f8eb --- /dev/null +++ b/params_shard_227.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:124d2c7d42490a9c27ec717e24dc5a43ecc6cb7e3f5e4fc64a57a52857b08a4f +size 31100928 diff --git a/params_shard_228.bin b/params_shard_228.bin new file mode 100644 index 0000000000000000000000000000000000000000..d981589e9637480cfe6a7503453ee60ef1b169df --- /dev/null +++ b/params_shard_228.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:267344d1bce60a60685673b66f184f446ade4bce19d7707d86aea0815cf63ca3 +size 188088320 diff --git a/params_shard_229.bin b/params_shard_229.bin new file mode 100644 index 0000000000000000000000000000000000000000..af2c9074b5770f887ae04aa086de4b7af3686be1 --- /dev/null +++ b/params_shard_229.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb5e9228518209447129bd5d7c0ce5b4425b36340f83d079064ed2ae4b9e825 +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..98a4c234ff622a2d5f264c0a616c7f89fc0b59e7 --- /dev/null +++ b/params_shard_230.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488670d3e5fd786d3e722ab2d84661931e9624b0c0cd12276f6eb2fd5eb77ebe +size 33587200 diff --git a/params_shard_231.bin b/params_shard_231.bin new file mode 100644 index 0000000000000000000000000000000000000000..92283314db9707e6170d5aca6f8815c455605333 --- /dev/null +++ b/params_shard_231.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2070cfaf8d07097455784c0aeb09b7151e3c07351ff1d3514f7967daa0af9fb2 +size 26869760 diff --git a/params_shard_232.bin b/params_shard_232.bin new file mode 100644 index 0000000000000000000000000000000000000000..1aa32934860b2e114c5468b8dfd8e99d0d8a45cf --- /dev/null +++ b/params_shard_232.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a72aa440ed6893202021ba98479a9ea79617edb73f35c9ecd231abfd6d2e66 +size 93978624 diff --git a/params_shard_233.bin b/params_shard_233.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b5ad888ddcd49b4b979204f65433d67eed4cb3f --- /dev/null +++ b/params_shard_233.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2a8e22c4bb5b3864514e823920c2845e5a861a653a6fe8d728998bbc41dc28 +size 93978624 diff --git a/params_shard_234.bin b/params_shard_234.bin new file mode 100644 index 0000000000000000000000000000000000000000..90c1d6b0c9d760b6e0fb1269f1f87c8916b19ca6 --- /dev/null +++ b/params_shard_234.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2959166e9d90bd55f12145d1847d89fa5266a7da64f737571ec930cac083688 +size 31100928 diff --git a/params_shard_235.bin b/params_shard_235.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ea96818d8647152809f3f734e2bb07f728e8a51 --- /dev/null +++ b/params_shard_235.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2331998a15ef2f388cba6c1c772366012126bdf3572d4936df2c0ec9c164ad +size 188088320 diff --git a/params_shard_236.bin b/params_shard_236.bin new file mode 100644 index 0000000000000000000000000000000000000000..102496763fddd44829e895688f6314ec2a8f71b4 --- /dev/null +++ b/params_shard_236.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bfec92577baa80df75061d961c876acd414f56ea87ebe68d4079f3355e5e376 +size 23511040 diff --git a/params_shard_237.bin b/params_shard_237.bin new file mode 100644 index 0000000000000000000000000000000000000000..10b7a75d37bed90bb0cadaf256fea534be3a3085 --- /dev/null +++ b/params_shard_237.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2d11816713047132705fd7178c889e4614279d3d03744b4b3fb35993ecbe919 +size 33587200 diff --git a/params_shard_238.bin b/params_shard_238.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d361b847dfb113f98cf894e7a17e359f9cb22f9 --- /dev/null +++ b/params_shard_238.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18780183907e008bf2c798c2d03d373d9e28bc00c832f967faa6a433bad2584d +size 26869760 diff --git a/params_shard_239.bin b/params_shard_239.bin new file mode 100644 index 0000000000000000000000000000000000000000..1513f57d82c2ac9b0092df39f9edbfe960e4e945 --- /dev/null +++ b/params_shard_239.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:680c5c310cbd8649130206ec1c7448399ab4895beb1721649b284fe007b2febc +size 93978624 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e385da3f1a1b1643e4c65666e79733a2863a389 --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b021dc75ceb27b4c181e0bdddd2ac59afbbfb94bc3a0eed02613e1344cfa8fe9 +size 23511040 diff --git a/params_shard_240.bin b/params_shard_240.bin new file mode 100644 index 0000000000000000000000000000000000000000..21771135bf0cc205fcf874dca98714bb7a7e49c3 --- /dev/null +++ b/params_shard_240.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35f5dd14862fd7cb4d2881e5cf211ba123976bf4512e1b72f88a7a33a39553e4 +size 188088320 diff --git a/params_shard_241.bin b/params_shard_241.bin new file mode 100644 index 0000000000000000000000000000000000000000..c6b885e22c8d992c1e14052ee0d7579135a6c5da --- /dev/null +++ b/params_shard_241.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f0792f51100cc12cd2badeb55887f451a7c290000c1d37094f9414032120a9 +size 23511040 diff --git a/params_shard_242.bin b/params_shard_242.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0f5104ce3bc35af192d17168fb43c1e22dfe3fa --- /dev/null +++ b/params_shard_242.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa85cb7f9836a3614a24492a43b3a69d5e758f4e75115a999b3fa69bf7c36001 +size 33587200 diff --git a/params_shard_243.bin b/params_shard_243.bin new file mode 100644 index 0000000000000000000000000000000000000000..a1630f47d3d02a20e5491342b5581c5c6fef2185 --- /dev/null +++ b/params_shard_243.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:336d60edeffefaec6a40d94ad5c969808998b7b1e94e44bf572ab0ecae869124 +size 31100928 diff --git a/params_shard_244.bin b/params_shard_244.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac586c34d20a44b031aa0cf0ad333e1502ff602d --- /dev/null +++ b/params_shard_244.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec5982f7f53b61c79ff7866866f1f01914ad1c48fd719d2cecc82f9faa79608 +size 31068160 diff --git a/params_shard_245.bin b/params_shard_245.bin new file mode 100644 index 0000000000000000000000000000000000000000..765ce4fddbcb65989e9be4b88317f40f10be3d6f --- /dev/null +++ b/params_shard_245.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aff9414ab562a0cf71f54edf576033fe38631bc8357b19f960b4c7c7dd2a32b6 +size 33587200 diff --git a/params_shard_246.bin b/params_shard_246.bin new file mode 100644 index 0000000000000000000000000000000000000000..ad90afb3cd16818017f0d316cd9f1d0172a5f72b --- /dev/null +++ b/params_shard_246.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:686203867708f7a1448197ad35b12eea3fe7080afcd85f665ee309bf93c7a160 +size 26869760 diff --git a/params_shard_247.bin b/params_shard_247.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a8a7dabc8f7c74e782874a4d6fa6bbc7b4944b1 --- /dev/null +++ b/params_shard_247.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebdb3b2451e4b2a43891e6c78461552c59495cf19c63aeea5c8f03c4bb062a49 +size 93978624 diff --git a/params_shard_248.bin b/params_shard_248.bin new file mode 100644 index 0000000000000000000000000000000000000000..97fab54c0a80781a8857de91e04b296ab3819658 --- /dev/null +++ b/params_shard_248.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:509620a35785e11eecaf8e9e973a44e3eef94176200b6b8a4c1de7a6777bc1c6 +size 188088320 diff --git a/params_shard_249.bin b/params_shard_249.bin new file mode 100644 index 0000000000000000000000000000000000000000..7509fc317f50172d5ca4f9ce898a5c4656772fe5 --- /dev/null +++ b/params_shard_249.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63da3fc169b221d888f1cd5fcf43908d604d243cad2b281eccc67637e53041ba +size 23511040 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..63a0b59d66081fb2f243e9e51e1d8fce673b1f73 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4175576670d6d2f830457e49af4a49d42c8efb63cf0ac705cf6464d9b2a91aa +size 33587200 diff --git a/params_shard_250.bin b/params_shard_250.bin new file mode 100644 index 0000000000000000000000000000000000000000..5980678bcffdb64a932acc54f7fa63d81314c7b3 --- /dev/null +++ b/params_shard_250.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f9e872c2583ce01e3cea74ce39a80d2664fd336f8c03dc4769caa958f78539 +size 93978624 diff --git a/params_shard_251.bin b/params_shard_251.bin new file mode 100644 index 0000000000000000000000000000000000000000..183f322b940d80ce6fa904f42070568854ef626f --- /dev/null +++ b/params_shard_251.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5717d8ed369e3a7b2f390c3c8b9388b33e569ce66d8cecac28914d6cb5a8de0 +size 22712320 diff --git a/params_shard_252.bin b/params_shard_252.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a0470ad6493900f881bc6e1a2bbc07446058266 --- /dev/null +++ b/params_shard_252.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b21a5cf7ab1b2e0105c964c1bcb8ce9e5408429089219a35cc808083ad46a20 +size 188088320 diff --git a/params_shard_253.bin b/params_shard_253.bin new file mode 100644 index 0000000000000000000000000000000000000000..9db80985783d70e6731ed99749bbf3f10028e4ec --- /dev/null +++ b/params_shard_253.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5040937d80226004a9a4f70c5f16f0b83a3c85b5b0fbaf168547546c15223889 +size 23511040 diff --git a/params_shard_254.bin b/params_shard_254.bin new file mode 100644 index 0000000000000000000000000000000000000000..2da4e89a2c01b90c2af04f719e85351ed611157f --- /dev/null +++ b/params_shard_254.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ffdd47f04d7f6046a774f5cf1dcdd7e81e98b4fb8d8517599b4fe22ab752bb +size 33587200 diff --git a/params_shard_255.bin b/params_shard_255.bin new file mode 100644 index 0000000000000000000000000000000000000000..20baeab1ada8df8ed93d0d1ea04caab7444b80ca --- /dev/null +++ b/params_shard_255.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a505210430a6fffa36e4943850eda78e25502ef7805edb9cc0942ceaf48865a +size 26869760 diff --git a/params_shard_256.bin b/params_shard_256.bin new file mode 100644 index 0000000000000000000000000000000000000000..3f4641f181ff78993df04f9de826772e9d679036 --- /dev/null +++ b/params_shard_256.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0843ae793dec68e1beba4218d0d7c27cabcd27e0ecf70d6061e3631f02c78c44 +size 93978624 diff --git a/params_shard_257.bin b/params_shard_257.bin new file mode 100644 index 0000000000000000000000000000000000000000..64f2a2420bacf2e65d10e8fbddf3c960761e844c --- /dev/null +++ b/params_shard_257.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f55d5ca92282124df0767ab0327e7d528071a336acecbccf6b4222af8f7bb6 +size 188088320 diff --git a/params_shard_258.bin b/params_shard_258.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0a53ab03b702052021c8907960bd8de211c3d5d --- /dev/null +++ b/params_shard_258.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5881a94acd14611192b19e742049457374ede4ae9f983c398cd57f6cf29a002 +size 23511040 diff --git a/params_shard_259.bin b/params_shard_259.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf791188cc5a0e31a1c9f8f25bbbe9ee0145965f --- /dev/null +++ b/params_shard_259.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e59b5d55c506c9057ef56f01a02d80e2f73d7c2db353f855d1e55fdcc65757 +size 33587200 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f1e9341a33f271844e73a74c978e1cc54d33265 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878969568661512938668366bd69c22f3b0f586b7c184d2dc54e444805f9f2c3 +size 26869760 diff --git a/params_shard_260.bin b/params_shard_260.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe3be8e4dc8bc828f162bf0d93cecbb58be1b96d --- /dev/null +++ b/params_shard_260.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13abe751307c11a85c2a4233f40b789274f81a4a4b17e31cd2855b3cadcfb0cf +size 31068160 diff --git a/params_shard_261.bin b/params_shard_261.bin new file mode 100644 index 0000000000000000000000000000000000000000..381b0630641c2e9b68ba06b3a0e97f7532c1a20c --- /dev/null +++ b/params_shard_261.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45df1ea4947d62531b3da46216a4942422a4c82040acd337c666b218449739f5 +size 31068160 diff --git a/params_shard_262.bin b/params_shard_262.bin new file mode 100644 index 0000000000000000000000000000000000000000..8080be69be51528d97d31b30862cb52ecabd6ae7 --- /dev/null +++ b/params_shard_262.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b264c122d0e7e794fe9a293be49f5d1a97bf8573197e203e64da79d6df8fad1b +size 93978624 diff --git a/params_shard_263.bin b/params_shard_263.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce079abeb72afb9de6a312c1828439a2670c6fca --- /dev/null +++ b/params_shard_263.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5cc6c2e7b55dc92aaed258735ea15eefacc1207e5d1eb3e5ec907678084ad08 +size 188088320 diff --git a/params_shard_264.bin b/params_shard_264.bin new file mode 100644 index 0000000000000000000000000000000000000000..82d8992f90818b6303e22ac5eadf134a9f7e9688 --- /dev/null +++ b/params_shard_264.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22603f0ac7cce2d46fa654ed4d2df18efdbe9541a9ab4654a259fabad0b485c9 +size 23511040 diff --git a/params_shard_265.bin b/params_shard_265.bin new file mode 100644 index 0000000000000000000000000000000000000000..f77cd0be215b7040738831da6a6ae39a1a185091 --- /dev/null +++ b/params_shard_265.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef735a00876f86541202b9a4783b74a5c3ac429fa6a5a4a61a53657ce6f9e86 +size 33587200 diff --git a/params_shard_266.bin b/params_shard_266.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d26227c7ead5cedd696a5cb37cc685e0e72b2a3 --- /dev/null +++ b/params_shard_266.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:729f5ffc26155a3d1f1e078a26cc570a1a3a7b60886317ebcdec919f4eac7e1e +size 26869760 diff --git a/params_shard_267.bin b/params_shard_267.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe688efd6bfaaadcbffc8058032e28505af217e0 --- /dev/null +++ b/params_shard_267.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f027ba5488e5ee66a4d0e47734d5a85f71bed27ba5b535cf3b998d3a029723 +size 93978624 diff --git a/params_shard_268.bin b/params_shard_268.bin new file mode 100644 index 0000000000000000000000000000000000000000..b50c48d02e714ab7633cb8e22bf947216b69dd48 --- /dev/null +++ b/params_shard_268.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db1e11e9a2e5d5eae931d68112adb2027d6768f6fa0607851ef2ee9ba8d531ea +size 22745088 diff --git a/params_shard_269.bin b/params_shard_269.bin new file mode 100644 index 0000000000000000000000000000000000000000..ad550e13eff1ca748317f3b6d08b7bebd16a396c --- /dev/null +++ b/params_shard_269.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d4540f15d2611356cd81a1982d6a17679bcf69da1a3b2521ac5180176e1ee3 +size 188088320 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ffec245f506fcf81e2bc4dedb43575124fb3ecc --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5434d004c6ff4d34bfb827aab8f567a8caf614953c2d39327fd36ca29084f3c +size 31117312 diff --git a/params_shard_270.bin b/params_shard_270.bin new file mode 100644 index 0000000000000000000000000000000000000000..c2d0471164b7697b6e31c69d41f11ce84e739c07 --- /dev/null +++ b/params_shard_270.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5feebc8cf9c2cc4e8fcc8adfc17a1ab036785f49e9b69d2d8e8d8f3e351d47 +size 23511040 diff --git a/params_shard_271.bin b/params_shard_271.bin new file mode 100644 index 0000000000000000000000000000000000000000..54ab324358ff4d4e345534f0541ef1eff32eb14f --- /dev/null +++ b/params_shard_271.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b2a6eeaf83265b5b379593cf9a7f6df4ef7763bbe34c3a2b2c43e6e51b757b +size 33587200 diff --git a/params_shard_272.bin b/params_shard_272.bin new file mode 100644 index 0000000000000000000000000000000000000000..d2977f78b6d9c3ebf22f5cd62fab9df97b10950b --- /dev/null +++ b/params_shard_272.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cfb30db8bc4119af1ef869995aa6d45decac2bffce9643152f2df39ffb4b001 +size 26869760 diff --git a/params_shard_273.bin b/params_shard_273.bin new file mode 100644 index 0000000000000000000000000000000000000000..93656d5ab844a521a46a6dafc9ddf357c3c331d6 --- /dev/null +++ b/params_shard_273.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03e445baf0257a58b73e336ee486a8026da20b900d20faa76094e0c87a04965 +size 188088320 diff --git a/params_shard_274.bin b/params_shard_274.bin new file mode 100644 index 0000000000000000000000000000000000000000..e082bd4cc8c93abf15a4242cc71522949bc127a1 --- /dev/null +++ b/params_shard_274.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ad1ce057796a954b8a522e588219fcce6adcdd0b589d3ea286fef94d7256f2 +size 23511040 diff --git a/params_shard_275.bin b/params_shard_275.bin new file mode 100644 index 0000000000000000000000000000000000000000..7b68d8486fa50834395e09783884e229b711499d --- /dev/null +++ b/params_shard_275.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f6821739ecf888e863e457f63e03f276e29d53027c56609a46b05f9b57ea77a +size 33587200 diff --git a/params_shard_276.bin b/params_shard_276.bin new file mode 100644 index 0000000000000000000000000000000000000000..03e5f62064ffff5a028c8e8cfc41383f1c1a0dd7 --- /dev/null +++ b/params_shard_276.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad75a65224d379b5774ba92db07202fe65421f58558a9714eada0121505013c +size 26869760 diff --git a/params_shard_277.bin b/params_shard_277.bin new file mode 100644 index 0000000000000000000000000000000000000000..fab77b3c5834e2f630f9d9616f828a1f9b4603c8 --- /dev/null +++ b/params_shard_277.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf759b835d2084bbd235801858ccc3f4ab9d059a1816fcb81ee27a770123cd4c +size 93978624 diff --git a/params_shard_278.bin b/params_shard_278.bin new file mode 100644 index 0000000000000000000000000000000000000000..86c8db1b679c892c16fad34a321f270a64a9e1a5 --- /dev/null +++ b/params_shard_278.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d1f21d0cedcfcf2ac6f667b45b2c043e79ed0ab56461dfa5af4793ae78952e6 +size 26894336 diff --git a/params_shard_279.bin b/params_shard_279.bin new file mode 100644 index 0000000000000000000000000000000000000000..61262413a97434ce611b46597943234768b37949 --- /dev/null +++ b/params_shard_279.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09ea8cccf85d8534f36b8fc790cf79fc174f55aea14e133f5b22d477f93ee97 +size 93978624 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec7be679abfc796fca7aaa26aa774993b5615118 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d77aae260887a19d18a5c2304728d72a63b164086042efc0b6ea3ef084cfe3 +size 93978624 diff --git a/params_shard_280.bin b/params_shard_280.bin new file mode 100644 index 0000000000000000000000000000000000000000..69c1dbfd4240be96c5ae252d4219b335c8ed8ad1 --- /dev/null +++ b/params_shard_280.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d244f118305233a7580f7992bfce6d424753cc40b6c3d39e5f5bd1e8503ad8dc +size 188088320 diff --git a/params_shard_281.bin b/params_shard_281.bin new file mode 100644 index 0000000000000000000000000000000000000000..6f966fd950a22d7125706f15aa908eff16a661dc --- /dev/null +++ b/params_shard_281.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e3ff53cd905898a0548e14dca0dab4c66ec3b3fc009592de87845ba85da6ac1 +size 23511040 diff --git a/params_shard_282.bin b/params_shard_282.bin new file mode 100644 index 0000000000000000000000000000000000000000..5c53aed39e7a5d39e416a1223c8bbdf9df444c3f --- /dev/null +++ b/params_shard_282.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:626a681735dd3411ff09dd11cc7b785f454bc025dcc1c4d7e58da9cf57e9d5e5 +size 33587200 diff --git a/params_shard_283.bin b/params_shard_283.bin new file mode 100644 index 0000000000000000000000000000000000000000..93d98d6844a1ab3736dc08234c0deec1ae11757e --- /dev/null +++ b/params_shard_283.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885c9d3511cf35243cfe7bc6a65d77755ccf1e8d8dfc5633262e2f28c84dfe11 +size 26869760 diff --git a/params_shard_284.bin b/params_shard_284.bin new file mode 100644 index 0000000000000000000000000000000000000000..a64c664b15282f1ace8fd97ff75ba08487fc0a86 --- /dev/null +++ b/params_shard_284.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8baaf8a29ac4357047322cd2b290a55849caa28746694cd271bb1f10108d205 +size 93978624 diff --git a/params_shard_285.bin b/params_shard_285.bin new file mode 100644 index 0000000000000000000000000000000000000000..67a7c5cc9c4a11f7be874fbc987a2dd4f0a6b35c --- /dev/null +++ b/params_shard_285.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fe9f2d41bf2c257208a6bc09c84f90757f5d3b95bf825eba9d96d7428782f56 +size 31117312 diff --git a/params_shard_286.bin b/params_shard_286.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea2ef0b75bb64850b3e512c2078a1709b0a75e80 --- /dev/null +++ b/params_shard_286.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20d4b9d98ffb23356c049a8683a165b3265ffbcaaf38d600fb1108801bb3fab +size 188088320 diff --git a/params_shard_287.bin b/params_shard_287.bin new file mode 100644 index 0000000000000000000000000000000000000000..49c0f2843c71790af716b2b8885e8b6fc7353c16 --- /dev/null +++ b/params_shard_287.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934fc231bd31a71ad64358a7df7325ccaa8ff4675f73c0ab2448660af64e0cc9 +size 23511040 diff --git a/params_shard_288.bin b/params_shard_288.bin new file mode 100644 index 0000000000000000000000000000000000000000..665d6147c682ab6373cae5512273f96729bb8812 --- /dev/null +++ b/params_shard_288.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c06890e21a92ae212b407e7fe395b6ec39d79332ec41cda22066094e2a7473 +size 33587200 diff --git a/params_shard_289.bin b/params_shard_289.bin new file mode 100644 index 0000000000000000000000000000000000000000..827423c289dcecda1b40ce8eede0bba5adb4879f --- /dev/null +++ b/params_shard_289.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d77cd749995176bfe0445925527047b797436be2fd0a1821cda8f54aa48f037 +size 26869760 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..c9cef8a16cfdd9c778f56153e1e7b6f866f4346e --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32f019060ae8e89f14ce7421640b6db90ae3a8313cf94a74bc590de6acf691cc +size 188088320 diff --git a/params_shard_290.bin b/params_shard_290.bin new file mode 100644 index 0000000000000000000000000000000000000000..8bcbf13dd60f6afdce0c6ce7e652961599b25512 --- /dev/null +++ b/params_shard_290.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947d86f8702d1e3c1b20bcd7d858ba5f2dbfb52200de1faa836a95008756d1d2 +size 33587200 diff --git a/params_shard_291.bin b/params_shard_291.bin new file mode 100644 index 0000000000000000000000000000000000000000..a72d85bc5dcf0d7c236eb62d7a251f425f7553c9 --- /dev/null +++ b/params_shard_291.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd237dfdb81a361b1a9735f1202e504bd68e662826503775e8a4b94a1611c66 +size 26869760 diff --git a/params_shard_292.bin b/params_shard_292.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e9b8e31609e6cba22d93a84eac8081a20487d86 --- /dev/null +++ b/params_shard_292.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cc5f4f92b4994cfd36e9b966607afc8f3520c23bf12d3e22d3611b0055bd53 +size 93978624 diff --git a/params_shard_293.bin b/params_shard_293.bin new file mode 100644 index 0000000000000000000000000000000000000000..3297bb3c0eaaeccd8991f7d9e131642fc65694a4 --- /dev/null +++ b/params_shard_293.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d216ffcb1e82aa9616bea94e20e1426089a7c1740fccaebb3651641d8b38994 +size 26894336 diff --git a/params_shard_294.bin b/params_shard_294.bin new file mode 100644 index 0000000000000000000000000000000000000000..974464165545c4fb7a2db62143ab27a033807959 --- /dev/null +++ b/params_shard_294.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b2c30482826ae8d01e00401caf783e28c5c3d40a985511b8cc01621742e58ba +size 188088320 diff --git a/params_shard_295.bin b/params_shard_295.bin new file mode 100644 index 0000000000000000000000000000000000000000..b7edf6f7a83e450b5aede8259ac2403abb66a720 --- /dev/null +++ b/params_shard_295.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f30b26493d870ab2bb755c0dd115376b79b339bcd874e7ca26267f41fb55394 +size 23511040 diff --git a/params_shard_296.bin b/params_shard_296.bin new file mode 100644 index 0000000000000000000000000000000000000000..f6a4800e3334e15ecb9fa28b6d597d1d9a27e4ae --- /dev/null +++ b/params_shard_296.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e694ab536a4b7b9819759611ebd679b02c48e77ff53c46fd4d642805c99701b +size 93978624 diff --git a/params_shard_297.bin b/params_shard_297.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c78ddf0cb7abad6d0701f2b71bb8f5b501dc473 --- /dev/null +++ b/params_shard_297.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9169cb4e45f59df27a9aeea0636288d3083056ceea1708b29878cddbe5d5ee3 +size 188088320 diff --git a/params_shard_298.bin b/params_shard_298.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e402b69526a3e4e71c8a368d9ffea8fb4dfec34 --- /dev/null +++ b/params_shard_298.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0504223dec01aeeb95b327b80bdd928efe151832c871b9088ea368e339c96b5e +size 23511040 diff --git a/params_shard_299.bin b/params_shard_299.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd72223afae3bad77be70975357e675ffc0f350c --- /dev/null +++ b/params_shard_299.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36f7108f7d23b6194203feb58e3bfe2621936e18deb20da266c7e8632c5cbaaf +size 33587200 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..f536be0ca7bf6626ef8b79bc476b9f501d5275db --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18b6f6c615330ea1b2f5e975cc18801916907e42ae3df23f03774497c7dc227 +size 93978624 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..536fce1e75aa76eca83ecb927385acd19bf4ebcf --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8e04807a11019402dae80857b3a945d77fed0e34cd0ad5236358cfa12609fa +size 23511040 diff --git a/params_shard_300.bin b/params_shard_300.bin new file mode 100644 index 0000000000000000000000000000000000000000..5461f1fc353c958c1e014c4741a15c36c3300f25 --- /dev/null +++ b/params_shard_300.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da0a664e968b886b527e1416ad1c18fc55236388f4e561695c9d32d1ae16233 +size 26869760 diff --git a/params_shard_301.bin b/params_shard_301.bin new file mode 100644 index 0000000000000000000000000000000000000000..fce9de8a639eebbb2fa0fe49f2eac7dec0c956b4 --- /dev/null +++ b/params_shard_301.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2b1660785fdec1471fe5aac802f8ffca418708052d37e2cd98cadef4e833f8 +size 93978624 diff --git a/params_shard_302.bin b/params_shard_302.bin new file mode 100644 index 0000000000000000000000000000000000000000..b6654773307ed113409d6cf350df473aec0f1818 --- /dev/null +++ b/params_shard_302.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d98dfd9f230c159907443bcb651f6949eb2a7f7b686c7d9b9f8170741ae7f9ea +size 31100928 diff --git a/params_shard_303.bin b/params_shard_303.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa2e7ccd8a8aab64edafac92011179cea93577b4 --- /dev/null +++ b/params_shard_303.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3e19ed36b512f0b2c1475809c42bce65dc27cf16f48121ff55142cf87d5cab +size 188088320 diff --git a/params_shard_304.bin b/params_shard_304.bin new file mode 100644 index 0000000000000000000000000000000000000000..0fb624945878e77da006adc67202fd7bbdbcdb13 --- /dev/null +++ b/params_shard_304.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc08567448c672fafafebc1cc63c30070cad2a9c486dd9118ae2cfe0b2786887 +size 23511040 diff --git a/params_shard_305.bin b/params_shard_305.bin new file mode 100644 index 0000000000000000000000000000000000000000..e8d298926f2a63f9f6976016e635751db71fb5d6 --- /dev/null +++ b/params_shard_305.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853d6b58330a32a06525cd932f4f0cac3ce2eebd1f88c50a73454c5c49ca61b7 +size 33587200 diff --git a/params_shard_306.bin b/params_shard_306.bin new file mode 100644 index 0000000000000000000000000000000000000000..b677386d0c4116fee54c9f7559e0d4055f084f00 --- /dev/null +++ b/params_shard_306.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a4145765cf8e0092d4ba05c59e5390eda215b4e65ba75869a6f4ac3ebf22e6 +size 26869760 diff --git a/params_shard_307.bin b/params_shard_307.bin new file mode 100644 index 0000000000000000000000000000000000000000..5bdf30a8ae53cb3f1851828b2e65906787eb1250 --- /dev/null +++ b/params_shard_307.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947ae5cb6ee462ccc482abeca08fa595b40f9999659d7b7c13281f798ab57c69 +size 93978624 diff --git a/params_shard_308.bin b/params_shard_308.bin new file mode 100644 index 0000000000000000000000000000000000000000..dab98ec630cf2d6fc95202b5cda69703d1754c9a --- /dev/null +++ b/params_shard_308.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a50c5e4935bbbc8b5e6baa8722965c2d3381fd3ad5096644b8acfb905da44da6 +size 188088320 diff --git a/params_shard_309.bin b/params_shard_309.bin new file mode 100644 index 0000000000000000000000000000000000000000..617c146f35c79ad8bddf65e57c647e48ded4b579 --- /dev/null +++ b/params_shard_309.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c89e160ee3ac775deb802804eb643a962dc75fc70d7353fc0d3852133c986dd +size 23511040 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..c3f634ed2240a5e804f7a5268d3b39111afc2f08 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f56ce7628a98db6ae19482ac8e76453d22c04d5eb0be5a4e058a2d48ed0b189 +size 33587200 diff --git a/params_shard_310.bin b/params_shard_310.bin new file mode 100644 index 0000000000000000000000000000000000000000..d694f841d23e569c95fd12d7d5e51fc5697d5636 --- /dev/null +++ b/params_shard_310.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc8105331a8815a645fb4bb0d28829ba4a50f1764599028f930963325622c1e +size 33587200 diff --git a/params_shard_311.bin b/params_shard_311.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f4b7067e50844456b6ddacc83de6b98e61a9a21 --- /dev/null +++ b/params_shard_311.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78aeab9d48ec5079bae6c0f62495209c89816837cb2771b0df97e8b0afd47538 +size 31117312 diff --git a/params_shard_312.bin b/params_shard_312.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ca36e2608ab46ebc23c12e9b45265aa135f993d --- /dev/null +++ b/params_shard_312.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b482029d10a3f09a5644d5febe5e8e4bf5772abb55b1ec78affb72abf2a912 +size 31068160 diff --git a/params_shard_313.bin b/params_shard_313.bin new file mode 100644 index 0000000000000000000000000000000000000000..babe74b6ad5ab1e0edcfd9e0d8db90bbe0fba363 --- /dev/null +++ b/params_shard_313.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef40c849c2a6eef956e2bc33d4663c4b6b7d4c6cca7be3a244b8d06171cc14bf +size 93978624 diff --git a/params_shard_314.bin b/params_shard_314.bin new file mode 100644 index 0000000000000000000000000000000000000000..65edac56bc9cec4229d58483888876d481b33425 --- /dev/null +++ b/params_shard_314.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78be6f225c8f4ee6890f3f392812d3b2724333cf9e9f27484273851fbd33a1d +size 188088320 diff --git a/params_shard_315.bin b/params_shard_315.bin new file mode 100644 index 0000000000000000000000000000000000000000..0aa29a5f6d90e100b8650406f2f29f3fb7784167 --- /dev/null +++ b/params_shard_315.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760f7c51ce7143860940f3e3cc664fda9aaf1a85d2ba81534795ffc985547ee2 +size 23511040 diff --git a/params_shard_316.bin b/params_shard_316.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e6bab2685dfa0e1f72d55706f8fda61019b8db2 --- /dev/null +++ b/params_shard_316.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0fc529073fde08158d3f1b2c1f6d7ebd83e69c7c7e13c95dcaf708f6e9ca8a +size 33587200 diff --git a/params_shard_317.bin b/params_shard_317.bin new file mode 100644 index 0000000000000000000000000000000000000000..287f4b6c20cfad82b4077cbcf9b0f05509507818 --- /dev/null +++ b/params_shard_317.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31082e31d56eebdb65b9c4a4a32b7bd9fdd9beb9b2eebf00cfa811d8da74f81d +size 26869760 diff --git a/params_shard_318.bin b/params_shard_318.bin new file mode 100644 index 0000000000000000000000000000000000000000..1268cda318b0c78144d41fc763465f23512c2086 --- /dev/null +++ b/params_shard_318.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70986231c16c4fa68a08d78e41eb08c76d567a97d38d37319440a27cf1ba14e +size 188088320 diff --git a/params_shard_319.bin b/params_shard_319.bin new file mode 100644 index 0000000000000000000000000000000000000000..9176c8107792a1074c621191445478153ae6e410 --- /dev/null +++ b/params_shard_319.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9debae5515161bc53ac8c03eac269ce37c5b278689fcfdda831e87d1a1d51c9 +size 23511040 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd5ccffec536b6d112743399bdc388837efcc01e --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c795597d0b52aff8ac808b73d5fc61b629eb334ade44f9fd73b2cf24250ced +size 26869760 diff --git a/params_shard_320.bin b/params_shard_320.bin new file mode 100644 index 0000000000000000000000000000000000000000..42c1015e4d078721cf6c0e947ecf5074de8b71b9 --- /dev/null +++ b/params_shard_320.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d88d8e5af1c33bf670405df3b6b8aa39becc3c4a573d3487caf3bddc31156d79 +size 33587200 diff --git a/params_shard_321.bin b/params_shard_321.bin new file mode 100644 index 0000000000000000000000000000000000000000..a4bdd3a46e0453249cc05db352993b9e95e181bb --- /dev/null +++ b/params_shard_321.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a18bf745e27ee4888e57561eb10888c2f688e8211ee1e744bf7ad876335249ed +size 26869760 diff --git a/params_shard_322.bin b/params_shard_322.bin new file mode 100644 index 0000000000000000000000000000000000000000..8fb057ad35f2e39a371a468b8b4d2ce3bbd5dfd5 --- /dev/null +++ b/params_shard_322.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72e6a66052590e0181f1ce8b32d6b1bdcca987956b4f476129fe3ba06e55738 +size 93978624 diff --git a/params_shard_323.bin b/params_shard_323.bin new file mode 100644 index 0000000000000000000000000000000000000000..d84a276dd635666c51ecfdaa46e58320f85dc8d6 --- /dev/null +++ b/params_shard_323.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb55294912568da907ff75405b3269d713d7c1b8da9e6b463fbec9674f0d086 +size 30269440 diff --git a/params_shard_324.bin b/params_shard_324.bin new file mode 100644 index 0000000000000000000000000000000000000000..1835d5241fdda188a3ab6fede1b7a2a5bc0d681e --- /dev/null +++ b/params_shard_324.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14c9e3a76d7f5ae66b916b7dacb02d01358996bfef1536c28a77079c41209a13 +size 93978624 diff --git a/params_shard_325.bin b/params_shard_325.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc5022c1cc0202c6867ab63743e9ca7dcbc63ed3 --- /dev/null +++ b/params_shard_325.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d720e73606e595143457b57f4ae9807c4a84820a8dbcbde71c44128fb9f8887 +size 188088320 diff --git a/params_shard_326.bin b/params_shard_326.bin new file mode 100644 index 0000000000000000000000000000000000000000..60e5774d24eb0d91ad65e99e12e20624a0d8f06d --- /dev/null +++ b/params_shard_326.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1467b1ebc8025f89ec7c112d5ac91e65679d75cabd4ac1c30feac762f474317e +size 23511040 diff --git a/params_shard_327.bin b/params_shard_327.bin new file mode 100644 index 0000000000000000000000000000000000000000..5454b79539fe466f2ac82160b802e1b73d8588c2 --- /dev/null +++ b/params_shard_327.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:516dff9c9d5f1d729c2b1335a9111eddd14b9525240770cc9a8e729a84dfbab4 +size 33587200 diff --git a/params_shard_328.bin b/params_shard_328.bin new file mode 100644 index 0000000000000000000000000000000000000000..6072791b4efad433f26e70e7f11d8977fa6187ae --- /dev/null +++ b/params_shard_328.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:444fdb08e9e65c2accd2ae89253db88062bdecd348eeaa5ad95380eaba79522c +size 26869760 diff --git a/params_shard_329.bin b/params_shard_329.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecf69c06eea2c3bc33f953c612faf77b4b7479a4 --- /dev/null +++ b/params_shard_329.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0054141c7ef254e040443e958d9883ba86a7ce471a2b6c11ecca7dd89b794bd +size 93978624 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..3432e77d86fc7a63feaa1dbf6516c4415006f8ad --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db682611d48486443239f5c224380ec3011f22053c96152de2b19a0afef8b3ff +size 33587200 diff --git a/params_shard_330.bin b/params_shard_330.bin new file mode 100644 index 0000000000000000000000000000000000000000..f5d2b8d3ed4deecf97c3709b8339bfff12dcc1da --- /dev/null +++ b/params_shard_330.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bddccbedc11597384db27e62f075b3b9b91491c1540d5bc0706d074dffbf1d56 +size 31117312 diff --git a/params_shard_331.bin b/params_shard_331.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1661e51754f5ab89ac5d2447c660c4cb7438713 --- /dev/null +++ b/params_shard_331.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d664ffdf0ab6e483bedb44e2549e519421669c41b23dafd60775252c8a7b7184 +size 188088320 diff --git a/params_shard_332.bin b/params_shard_332.bin new file mode 100644 index 0000000000000000000000000000000000000000..3afcbd6071ec1304b7188545a465c51de9c38a47 --- /dev/null +++ b/params_shard_332.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a032b57f4ddb9e59577a055b5ba02f0b1e28fd15fa9061d639014a01bbc7e9 +size 23511040 diff --git a/params_shard_333.bin b/params_shard_333.bin new file mode 100644 index 0000000000000000000000000000000000000000..adc8ea95a3cd73a51b50fb60c24463385dc6d507 --- /dev/null +++ b/params_shard_333.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:915b819fee4a6b387531bd1de99851a45b16545364e8c06473ee1bfecdc7b7b8 +size 33587200 diff --git a/params_shard_334.bin b/params_shard_334.bin new file mode 100644 index 0000000000000000000000000000000000000000..89354b6dfd9e778c68f4b5dd8d051fa1e6ed106c --- /dev/null +++ b/params_shard_334.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca3ea6cb924aefaff6427a2fbc1520589732c450d32d57945a578bc86cc4c890 +size 26869760 diff --git a/params_shard_335.bin b/params_shard_335.bin new file mode 100644 index 0000000000000000000000000000000000000000..cf552a9c8eb3a5cb6692003be2442a914dba8cac --- /dev/null +++ b/params_shard_335.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ae1fc978e6379f63ed4a42bfb3dbff57ded159300f2c4bd0964791cddac0c5 +size 33587200 diff --git a/params_shard_336.bin b/params_shard_336.bin new file mode 100644 index 0000000000000000000000000000000000000000..0da7bb4b8ea7c546f9914d1f239dc4874885eaf5 --- /dev/null +++ b/params_shard_336.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19cfa7c50e5caa632514d097d6081f0db285019b4222d74b4ba59a7ca1160a63 +size 26869760 diff --git a/params_shard_337.bin b/params_shard_337.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2ebd354bad19945611c07b12c03bf7c56221e03 --- /dev/null +++ b/params_shard_337.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aec144baa066b2c1bc7faf26c98daf3ff2c205ffa529f50d59f0b5899234662 +size 93978624 diff --git a/params_shard_338.bin b/params_shard_338.bin new file mode 100644 index 0000000000000000000000000000000000000000..6cef81bd169e9974a1b7cbc95498dfd4a6de27bd --- /dev/null +++ b/params_shard_338.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde2c32d2a7184066c07e96ae1c09195d242d86df807f9aafb174ac62f733eef +size 26927104 diff --git a/params_shard_339.bin b/params_shard_339.bin new file mode 100644 index 0000000000000000000000000000000000000000..d810bf61ac6fcb802835bc0eed9941c2b2c55f5f --- /dev/null +++ b/params_shard_339.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6609ac32c3720c4c1be534f93005924a706d9187b52cd5d6b299f34332fa754f +size 188088320 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..a376b36f89a5deb6893c1ad2b1a20fd737fdf757 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32240c3c23cab7f900e0d84fc3cdb0b9b9701b8c218865c2f44e71188322decc +size 26869760 diff --git a/params_shard_340.bin b/params_shard_340.bin new file mode 100644 index 0000000000000000000000000000000000000000..b6f3bdad188ba99c0c342e5b9455923abf491c65 --- /dev/null +++ b/params_shard_340.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce8dd8ae03f358a5ad96831d91d7bd0bbf562fb12e02a8884be4691be384d33 +size 23511040 diff --git a/params_shard_341.bin b/params_shard_341.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8cfb0dc03cf8a78043633a5277fe64e6582c286 --- /dev/null +++ b/params_shard_341.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b81a382628f1fdf7494313e733849fde08515d79fab2a2a19e2c2efff3b0cbd3 +size 33587200 diff --git a/params_shard_342.bin b/params_shard_342.bin new file mode 100644 index 0000000000000000000000000000000000000000..44f53b98aef4969115af9568b29c5965564e46de --- /dev/null +++ b/params_shard_342.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619789a6bb51a9d3cdb166e73d1669b54a5fbfc3a7910be5b3732c4c086d84b3 +size 26869760 diff --git a/params_shard_343.bin b/params_shard_343.bin new file mode 100644 index 0000000000000000000000000000000000000000..0536f2b1e8f47259141a07e40c293f75eff311f3 --- /dev/null +++ b/params_shard_343.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce617aa2f777b0b26041a7d6fca69e4769daf9b64008a8b577d7e5949f75a6ab +size 93978624 diff --git a/params_shard_344.bin b/params_shard_344.bin new file mode 100644 index 0000000000000000000000000000000000000000..f738c5b0b3827f4cebb4ccd2f68f80af664150ed --- /dev/null +++ b/params_shard_344.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3498839ec0cc278e4a4e2be6687a8bdd08909fa3a9b656bd1bd096c15da2c9c4 +size 188088320 diff --git a/params_shard_345.bin b/params_shard_345.bin new file mode 100644 index 0000000000000000000000000000000000000000..eee7bbd4b49a7b60638cc5034ccedf2b1f4b118a --- /dev/null +++ b/params_shard_345.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4388c9c01b130c90a8b26c6e24e3c4b46758d687213fa15a35437a16b2cdd7 +size 23511040 diff --git a/params_shard_346.bin b/params_shard_346.bin new file mode 100644 index 0000000000000000000000000000000000000000..11467419bf15c1d9ff7cc46228f8a16036321847 --- /dev/null +++ b/params_shard_346.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7afdd10b3678eb0d13a21130e5dc8c269ea81fe545a1aa1e896c1e25ab702d17 +size 33587200 diff --git a/params_shard_347.bin b/params_shard_347.bin new file mode 100644 index 0000000000000000000000000000000000000000..01b565954154d641d866a37e8e0a4e94a0815507 --- /dev/null +++ b/params_shard_347.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19f769b3ce4c0c5fc05d71575455f4ff1cb43599defbeda4261671131444283 +size 31100928 diff --git a/params_shard_348.bin b/params_shard_348.bin new file mode 100644 index 0000000000000000000000000000000000000000..60c01c5e2f4f6095430e808348a06fedcdca2873 --- /dev/null +++ b/params_shard_348.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f2f534f36e84824af05cb3ef6e0ca7d25afe239e82de3d274aa0fe6fbd94a1 +size 31068160 diff --git a/params_shard_349.bin b/params_shard_349.bin new file mode 100644 index 0000000000000000000000000000000000000000..c2a67c80c474a6fd5fd5b6f4c6d6a2c2ef885109 --- /dev/null +++ b/params_shard_349.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f84b796cf7cfb94abd45af5eaa35689aac37eaece9b6e1998089b244298d53 +size 33587200 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..38785fc3b5919b101765387061293b264987467a --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dbdd26ab61a37f5b1a386eb04a03ce101b7463219e20eb6e59db0994d3ccc9e +size 93978624 diff --git a/params_shard_350.bin b/params_shard_350.bin new file mode 100644 index 0000000000000000000000000000000000000000..1641bee5e6288dd3f6816a1cafe4c53697e471db --- /dev/null +++ b/params_shard_350.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12fd93e479e7ce88bfec77df85520e1f7810523c7c98023ff423457ce04aac28 +size 26869760 diff --git a/params_shard_351.bin b/params_shard_351.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef440017bb1aac1a247520feef165a2dfffa90fe --- /dev/null +++ b/params_shard_351.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2e003204b2a10681fd72f8fadb34703a8ac293a899dcc14e46bcb7803bb484 +size 93978624 diff --git a/params_shard_352.bin b/params_shard_352.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1f79cf51351256ec45b51354ee6c9e64cc24d96 --- /dev/null +++ b/params_shard_352.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb3713f2e7dafae48a54167b08e6b8be1493ea74c1820e2991c317c15e66fc3 +size 188088320 diff --git a/params_shard_353.bin b/params_shard_353.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf7f3ea2f5bcfbada886c0819316b841dc4acf38 --- /dev/null +++ b/params_shard_353.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a7071c1e3482f1f0c07638e8aaf9daae505c5e17ed02a3e03aa469cdfbe09e +size 23511040 diff --git a/params_shard_354.bin b/params_shard_354.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c2936a6ff4fbb0116e65fe820518bc03d91e47c --- /dev/null +++ b/params_shard_354.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6109bfe13007f02bca1a92aad51e41ff6c28886f34ee273f94760b55ceafdc92 +size 93978624 diff --git a/params_shard_355.bin b/params_shard_355.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c3a0392ec5ce2e7909e71acc54305385ddb1811 --- /dev/null +++ b/params_shard_355.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eee1ddbe027b31300c6aea913233e1910e4d218b7485588c784f5579c5c6f412 +size 22712320 diff --git a/params_shard_356.bin b/params_shard_356.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d87ef0c562dad8c1701c1fc84571bd2cf17c8f0 --- /dev/null +++ b/params_shard_356.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8583e3dc95d49c964d0c9781b529e63875248d049e21216513e5cb5ab228ae28 +size 188088320 diff --git a/params_shard_357.bin b/params_shard_357.bin new file mode 100644 index 0000000000000000000000000000000000000000..3c1f5766ba8ebec98284a27ff1422ce136684069 --- /dev/null +++ b/params_shard_357.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6293a9daf659443177ea0ef771d29beba832bfdd0945665117379746533f703 +size 23511040 diff --git a/params_shard_358.bin b/params_shard_358.bin new file mode 100644 index 0000000000000000000000000000000000000000..571d0da0d511779009503e7024e8aafe7f85530b --- /dev/null +++ b/params_shard_358.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b63711d40958adc5867d4117b793e4b9461d4b5a9a282c6611e13d205e4c6bfe +size 33587200 diff --git a/params_shard_359.bin b/params_shard_359.bin new file mode 100644 index 0000000000000000000000000000000000000000..472c3fe32acb9be94545acf1019770cb2c325c0c --- /dev/null +++ b/params_shard_359.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acbb5c72653f85d51ccafd14900d02b0d29e0db80bdb4a328b2496ededf6abfe +size 26869760 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..a619be69a373cafcc150fe3cf1dabb557f418ee7 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ce5d07af305ab6b483b02c5034f8520c2fc508db12ee911cb68feac2e42b75 +size 30269440 diff --git a/params_shard_360.bin b/params_shard_360.bin new file mode 100644 index 0000000000000000000000000000000000000000..3fa7be5258d04a4c16c8dd8ddb5e315adbc9be7d --- /dev/null +++ b/params_shard_360.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78299f7ebe2bb0810220d6b241220b3a37a95887967ee8a88339a8e602363bb1 +size 93978624 diff --git a/params_shard_361.bin b/params_shard_361.bin new file mode 100644 index 0000000000000000000000000000000000000000..15571b3fd903891eb796d36a05776ae92473e62f --- /dev/null +++ b/params_shard_361.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da1698f952f8382cf8db94471c3b35f0851a3f1a6e55e57d9945f057980bed95 +size 188088320 diff --git a/params_shard_362.bin b/params_shard_362.bin new file mode 100644 index 0000000000000000000000000000000000000000..99c6878627ded5a7e0569a97fad5afd8b8665eb1 --- /dev/null +++ b/params_shard_362.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7afab927c2d4c9806d8c0a918788f46abe71f75d614c276761aabefbc4965355 +size 23511040 diff --git a/params_shard_363.bin b/params_shard_363.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d99bcd0cab42029aa46448f86a2ec6129313663 --- /dev/null +++ b/params_shard_363.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ec1927da0af1e4dca806056d0ef9c297796c22ca0dda83d3dac267e6e52bb3 +size 33587200 diff --git a/params_shard_364.bin b/params_shard_364.bin new file mode 100644 index 0000000000000000000000000000000000000000..850dde9227faef89a70164f63b42e334de08823e --- /dev/null +++ b/params_shard_364.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b0ea69da1c4fea7051cae8f1b9f9f881f67b5b7b7eff9d5caa83a31355450c +size 31068160 diff --git a/params_shard_365.bin b/params_shard_365.bin new file mode 100644 index 0000000000000000000000000000000000000000..17eabe14849588562a395feebb72d3cb7ebab00c --- /dev/null +++ b/params_shard_365.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45cf40bce538f57815ac569a271656eef587c78e6f4f69dc5889505691ee4e63 +size 31068160 diff --git a/params_shard_366.bin b/params_shard_366.bin new file mode 100644 index 0000000000000000000000000000000000000000..d001a98ecea3ddb00389dc4b7925a18dc727298f --- /dev/null +++ b/params_shard_366.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ba1cb270f6da6957b58994073fce96a22cd8f95858dca278b8bee8082356c4 +size 93978624 diff --git a/params_shard_367.bin b/params_shard_367.bin new file mode 100644 index 0000000000000000000000000000000000000000..6fa4205175db54a347593269bd8f0bf246604cab --- /dev/null +++ b/params_shard_367.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3408cc12f78f7c1e8c246e59894cc0215ca7e7e4b7ae5a930a37cb3091ad5936 +size 188088320 diff --git a/params_shard_368.bin b/params_shard_368.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b9159dc33a30f0030b78714e4d68a072429c8ef --- /dev/null +++ b/params_shard_368.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc622feeabbb194150f8412f4f6a08832ccf56b6796c7b3a869f1736cf07569 +size 23511040 diff --git a/params_shard_369.bin b/params_shard_369.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d9f3655297f699b9341c8181ac6eb2ce33a3bae --- /dev/null +++ b/params_shard_369.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545dafa5235f18e4ef5b02a65234fd983395ce3546f567152a7936c8ed1ad970 +size 33587200 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b1c1fa982e097fda1b425410d30e22c9f27032d --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04227faa18608a5a115c282706a37ca9fcee87bbb6a5e76af863fc1d6b75ddc +size 188088320 diff --git a/params_shard_370.bin b/params_shard_370.bin new file mode 100644 index 0000000000000000000000000000000000000000..d51b79a26416fd34641b01101b32bd1d6549bdf0 --- /dev/null +++ b/params_shard_370.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58f400fc49ed539b0d2defcacda9b83e3afee8bb31e430efd66e54ddf675214 +size 26869760 diff --git a/params_shard_371.bin b/params_shard_371.bin new file mode 100644 index 0000000000000000000000000000000000000000..360374ec332aca332c188315ed27fea43aceaa44 --- /dev/null +++ b/params_shard_371.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e33bb576b17507e7ab7967cdaadb524f3cc52cc8463c3ccb976531d754121f63 +size 93978624 diff --git a/params_shard_372.bin b/params_shard_372.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2b31ca67f967b71c7edbc0e123507189eb9fdc9 --- /dev/null +++ b/params_shard_372.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f061c2a797dc6122811100bdf6e5af96fbb1c75948a1463647e27202b2a244 +size 22745088 diff --git a/params_shard_373.bin b/params_shard_373.bin new file mode 100644 index 0000000000000000000000000000000000000000..759bc6c6eb877dcee2165a64662aaba25d7e7961 --- /dev/null +++ b/params_shard_373.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad4dceb8f3eaf8fd66fe28731547fed2eddfddf528844e9b6bbc0f56d23b627 +size 188088320 diff --git a/params_shard_374.bin b/params_shard_374.bin new file mode 100644 index 0000000000000000000000000000000000000000..76aaa974eeabc654e15458560a4abe7978a5c666 --- /dev/null +++ b/params_shard_374.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2e97e60806a372e462d863fa13dfe5ecbb70e24f01c22a8c7b5fc10c30b001 +size 23511040 diff --git a/params_shard_375.bin b/params_shard_375.bin new file mode 100644 index 0000000000000000000000000000000000000000..09bd8585cea7aac8d984372835fd7aea3fb4704e --- /dev/null +++ b/params_shard_375.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f197dc0263234b01dafcb5765e83f6bedfa8e76f0327d0cb5cc3a36d1099174a +size 33587200 diff --git a/params_shard_376.bin b/params_shard_376.bin new file mode 100644 index 0000000000000000000000000000000000000000..e006bedf2031da5d66c7f01faa890ef7d2c9954d --- /dev/null +++ b/params_shard_376.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:017f4b17805aac0edd52afc15ba8cbe7c716512b2876822102ecdee6fee2798e +size 26869760 diff --git a/params_shard_377.bin b/params_shard_377.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7535176203924402e821e123d855387aac1d13e --- /dev/null +++ b/params_shard_377.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd3746b63a244a6fdcc59e9530d77fdccbab9702d08c1cc634cf579f43aace3 +size 188088320 diff --git a/params_shard_378.bin b/params_shard_378.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b105907806231acfc0c673f560e05fde1d44902 --- /dev/null +++ b/params_shard_378.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f5484241cb43a7b4bcdb076cabd4d338c27a31e3aee5242c295501a4436faf +size 23511040 diff --git a/params_shard_379.bin b/params_shard_379.bin new file mode 100644 index 0000000000000000000000000000000000000000..ad786626a60902a047a6f86f5571cf227e1418a9 --- /dev/null +++ b/params_shard_379.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6903407838d59552e750edf6f03e641053025d89556cc2e1219cc5404e3f1183 +size 33587200 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4b0ac673d228eeafaa3198ed5324d32ffd34622 --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d665553e24b27fb4f3e2821c715e80dc29ed3717f0e448959777934fd6e4e9a +size 23511040 diff --git a/params_shard_380.bin b/params_shard_380.bin new file mode 100644 index 0000000000000000000000000000000000000000..027215f12df725fc6de1e2e06647b5dfeea08795 --- /dev/null +++ b/params_shard_380.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b23f2ed1d5783c2b9df521074ee712e4806455ea32b4b027c98d333f6f24001 +size 26869760 diff --git a/params_shard_381.bin b/params_shard_381.bin new file mode 100644 index 0000000000000000000000000000000000000000..328f6d3ae775024efaac6ec2a8dc2fce4a9a04b9 --- /dev/null +++ b/params_shard_381.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7706cb6dacf98b1af0558c3812f0464c124fb8126322c77b63f62d85fd23d68e +size 93978624 diff --git a/params_shard_382.bin b/params_shard_382.bin new file mode 100644 index 0000000000000000000000000000000000000000..8a6076100460e1fadba5cb22995b85de17882ad5 --- /dev/null +++ b/params_shard_382.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71681e82e55e3e77d787c8355a8695ae39dd5de5066d66f03de7350c2843b87 +size 26894336 diff --git a/params_shard_383.bin b/params_shard_383.bin new file mode 100644 index 0000000000000000000000000000000000000000..57d534d52f6393c392020c3e37b10c9a1d15e9ae --- /dev/null +++ b/params_shard_383.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2769a24f9e426f25e2d6723a3cc9d4e7c194361a80f8bfc89fa70bae4023d1c4 +size 93978624 diff --git a/params_shard_384.bin b/params_shard_384.bin new file mode 100644 index 0000000000000000000000000000000000000000..42b3dae2eb0bff6d9f8aafdc09cd3dd1ffdcc457 --- /dev/null +++ b/params_shard_384.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0c05a70bc9c3829269267a3c0abbe090d1d87e2311a072426abcbd8a2a3857 +size 188088320 diff --git a/params_shard_385.bin b/params_shard_385.bin new file mode 100644 index 0000000000000000000000000000000000000000..55afc1deba39d1f59ed24141228995857685d626 --- /dev/null +++ b/params_shard_385.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a988434905b53c4d18ab556955afe31266a51c85820be630c02f9399fc4cc9e9 +size 23511040 diff --git a/params_shard_386.bin b/params_shard_386.bin new file mode 100644 index 0000000000000000000000000000000000000000..d7760cae1f53e7e043adaf8a63465e6f6b260699 --- /dev/null +++ b/params_shard_386.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a72d14250ef311ff3e2c755589932592af3d70838f8ba519d609c35e843bfed +size 33587200 diff --git a/params_shard_387.bin b/params_shard_387.bin new file mode 100644 index 0000000000000000000000000000000000000000..32e4a73e9bf79fa943326e25f8424aca535e176f --- /dev/null +++ b/params_shard_387.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4067221a26539ca5d413b37ffae0322ff6a16dbdd14fe2dd731e7a6039829984 +size 26869760 diff --git a/params_shard_388.bin b/params_shard_388.bin new file mode 100644 index 0000000000000000000000000000000000000000..6751c3c108231406d691ff8b37124f4392ecae21 --- /dev/null +++ b/params_shard_388.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6034864ebb1d4b9bf172be01640f301ba9bb9ac7297f84153ba71e95cc095feb +size 93978624 diff --git a/params_shard_389.bin b/params_shard_389.bin new file mode 100644 index 0000000000000000000000000000000000000000..fd62db1d72e41a9dcfd58ab887a356618c40f3cf --- /dev/null +++ b/params_shard_389.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53531ec38c22f9bb1b41f1c8234e00dbf5a724abdabcce07b30ecfd081423919 +size 31117312 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f641908cb3c51df0fd385bf89c3ea83cfa64ae8 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f124db819199f508dcbb4653a7bd36d44018026cbc8ef54654d9334b2c82b5a +size 33587200 diff --git a/params_shard_390.bin b/params_shard_390.bin new file mode 100644 index 0000000000000000000000000000000000000000..20d1d300d6971e3f292978ad8ff87da0b0af4239 --- /dev/null +++ b/params_shard_390.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65657e47f6b442149b722c8ed189cd3992a5e6602b5feb05ca644055e894afe3 +size 188088320 diff --git a/params_shard_391.bin b/params_shard_391.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e3dd6420c9c628ae2af1a1a0b37daed0f7d5809 --- /dev/null +++ b/params_shard_391.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352f6fed265e098c2d9226ac144e055971d7d8da9a524097414f04b6a0720e59 +size 23511040 diff --git a/params_shard_392.bin b/params_shard_392.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d9d4f232597b054c37cf8df6ea258a64612bba3 --- /dev/null +++ b/params_shard_392.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c14716aee80a83d76c02d8d2474ce947e8012eaea4417c38bdfbe3c04313789c +size 33587200 diff --git a/params_shard_393.bin b/params_shard_393.bin new file mode 100644 index 0000000000000000000000000000000000000000..61f688a071129432e88633f7725a5fcb5d763aa4 --- /dev/null +++ b/params_shard_393.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb55ca786fffef4bbf6b2a5aacae916745a4ee8bfe822aa9a92b8b5c13d27f57 +size 26869760 diff --git a/params_shard_394.bin b/params_shard_394.bin new file mode 100644 index 0000000000000000000000000000000000000000..b322c736935e50549ba346afb419802375b683cf --- /dev/null +++ b/params_shard_394.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:283adf91f1b46166a21a1e270f08256b164b95d6ad759331c5f41cbaa47cdfe2 +size 33587200 diff --git a/params_shard_395.bin b/params_shard_395.bin new file mode 100644 index 0000000000000000000000000000000000000000..db74dc352075380a94744e98dab8d771207a9b8c --- /dev/null +++ b/params_shard_395.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0420bb9c7f9b796b13d2308b41235c5bac05e0366b8fb7143ede54b5d2271351 +size 26869760 diff --git a/params_shard_396.bin b/params_shard_396.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b0eb34020b9e2f3a1ef0d54d5766d220520f3e2 --- /dev/null +++ b/params_shard_396.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4cf2b656328e6c859ecc456ba667a6cd312c8b68bb664104b2aac7c04c9925 +size 93978624 diff --git a/params_shard_397.bin b/params_shard_397.bin new file mode 100644 index 0000000000000000000000000000000000000000..c43a6c45a9d2e0ddf624b5fce57333a93de684bc --- /dev/null +++ b/params_shard_397.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a539163c5171ef25cb03dff53c8851d02803b5b368f128263dd3919a530057 +size 26894336 diff --git a/params_shard_398.bin b/params_shard_398.bin new file mode 100644 index 0000000000000000000000000000000000000000..0dbddf73d654991035d17efd59203d1bcfedd0c8 --- /dev/null +++ b/params_shard_398.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77fc67aeea97627e6a837f821e7438a99fcc3e60270645f4dbdb6d6a5dcf713d +size 188088320 diff --git a/params_shard_399.bin b/params_shard_399.bin new file mode 100644 index 0000000000000000000000000000000000000000..6aef702b7e8157a6c14f8c88b8b2aa198725d4a7 --- /dev/null +++ b/params_shard_399.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc8b068a43b7643de1a0482f12606a63f28c596ee0a167329241237e0028e019 +size 23511040 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..a671716246f507e395036522b66a95cdebb80d3b --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1fecb651a992d6c7f13ecb141b4d91ab7aed21312ae3ca687ae452f41f19d47 +size 23560192 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..9f28cb970093fda59bed451248f4b6999c8c2193 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9130a63099b04f430c987ab856d86df1f304bb0420765e264604042b65e49ef +size 26869760 diff --git a/params_shard_400.bin b/params_shard_400.bin new file mode 100644 index 0000000000000000000000000000000000000000..4e5e66a383f710d575fd44b88896c28d19ce5fbb --- /dev/null +++ b/params_shard_400.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c53f5713d2a23a47edae4632cb9f0908c00bc389ef21a42c1dd7c25c619b0cb3 +size 93978624 diff --git a/params_shard_401.bin b/params_shard_401.bin new file mode 100644 index 0000000000000000000000000000000000000000..31fd935952f52a54e530f33370a3e2100750496c --- /dev/null +++ b/params_shard_401.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296435850214e605a7f8304c7c65c6134858dfba1d0acd61ad773592b882b8d7 +size 188088320 diff --git a/params_shard_402.bin b/params_shard_402.bin new file mode 100644 index 0000000000000000000000000000000000000000..9671911aba11309f06af0ab8e2ac1405d41c2412 --- /dev/null +++ b/params_shard_402.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbe651c034c68e3d65c3f013cc9b5920beb6b92e9df8aeab0f283d82ed7905b7 +size 23511040 diff --git a/params_shard_403.bin b/params_shard_403.bin new file mode 100644 index 0000000000000000000000000000000000000000..8eae101e7b852e13a7a649744fa5b0951adde188 --- /dev/null +++ b/params_shard_403.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5574b8732aee9d32a54e248ea5d2a9cc8b64dfd0eda453dbe0212853a395108 +size 33587200 diff --git a/params_shard_404.bin b/params_shard_404.bin new file mode 100644 index 0000000000000000000000000000000000000000..9cd099510b478b8085dc1b3e335e11e256a09809 --- /dev/null +++ b/params_shard_404.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b9c58d3864834cc3b5571f3a069847edf3fed1645da0ab973bc1f133a210150 +size 26869760 diff --git a/params_shard_405.bin b/params_shard_405.bin new file mode 100644 index 0000000000000000000000000000000000000000..8123018f52c44e60aca5962f2cb5e9a8ccf831dd --- /dev/null +++ b/params_shard_405.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c14d4842a4d8fc24c10c6873a3c91cb3c8a82ebfdf97ba753ed27124f20a745 +size 93978624 diff --git a/params_shard_406.bin b/params_shard_406.bin new file mode 100644 index 0000000000000000000000000000000000000000..b351181b1f53c2296891d64f34cf34e6e7e0359d --- /dev/null +++ b/params_shard_406.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97e8d9df367aa2b4598fca77679ac8554cec552a614d33c621928a9aebb63620 +size 31100928 diff --git a/params_shard_407.bin b/params_shard_407.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f69484a365df58226c6e08b3addd24df93ddad0 --- /dev/null +++ b/params_shard_407.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f2f5c0d63a7c022c03963c60152b47d8347725ad268f3a91413b88a4da96257 +size 188088320 diff --git a/params_shard_408.bin b/params_shard_408.bin new file mode 100644 index 0000000000000000000000000000000000000000..8af2397caebe75747eb76f9bad20a789fc743f9e --- /dev/null +++ b/params_shard_408.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f223ae1dea65551b2be7f7ebd455733720079d86a5b7a3b4f77ea974233c59 +size 23511040 diff --git a/params_shard_409.bin b/params_shard_409.bin new file mode 100644 index 0000000000000000000000000000000000000000..c5ec7895ed121c367529e48b18ec9c578e9e0fd8 --- /dev/null +++ b/params_shard_409.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5e105825b7ff206ba59099938fc1d098e16de596162df88633959ebdd42e425 +size 33587200 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..372a9d0b48666577e68c5c8ffbbf6332d9dc2d7d --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d387d8eea1f76f02359e4d3c5f9178bd99cad3900a104b6c04f38f400ca775 +size 93978624 diff --git a/params_shard_410.bin b/params_shard_410.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc2b2edb1b23eb075991302df500659c63bf4dcb --- /dev/null +++ b/params_shard_410.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:407c6e0d63751ae5a207f398fec7404a8a8ab53f3158b69d0752dc97a98392ec +size 26869760 diff --git a/params_shard_411.bin b/params_shard_411.bin new file mode 100644 index 0000000000000000000000000000000000000000..310e1dccafeb75a85c8a5c3b6977008a6e6a214f --- /dev/null +++ b/params_shard_411.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91082103afa4208df423d09c7cd07674fbd30eea34277605989094a7d7cf7fe5 +size 93978624 diff --git a/params_shard_412.bin b/params_shard_412.bin new file mode 100644 index 0000000000000000000000000000000000000000..9023112eafd8b7c2fe8a17c289a3843391144dbd --- /dev/null +++ b/params_shard_412.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93af6f9ec680ff91bfaee51624ee20be7e6d06551d8cf37e6c421be8bb342df4 +size 188088320 diff --git a/params_shard_413.bin b/params_shard_413.bin new file mode 100644 index 0000000000000000000000000000000000000000..2277ab8bd6df885ee368e37fe0d1d53050ed334c --- /dev/null +++ b/params_shard_413.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4571c7892e1ce8d92308c184ab66da3473eba15275e242d532a7b113ebcb1aac +size 23511040 diff --git a/params_shard_414.bin b/params_shard_414.bin new file mode 100644 index 0000000000000000000000000000000000000000..a608cc9a75e9095d1eab91e2d7e2b71f29f4d075 --- /dev/null +++ b/params_shard_414.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0e4985aa266f55c3d22646f38c4e3d1cfb02b400d07bbc201eccddf7315e716 +size 33587200 diff --git a/params_shard_415.bin b/params_shard_415.bin new file mode 100644 index 0000000000000000000000000000000000000000..07e397ede614afe042f6cc8b3987c66ec34b76d9 --- /dev/null +++ b/params_shard_415.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ede6372b482713d7c60c597408af98fb891dea99ea086f79b539d261c391d6a6 +size 31117312 diff --git a/params_shard_416.bin b/params_shard_416.bin new file mode 100644 index 0000000000000000000000000000000000000000..c6751d86f065aac86e4eedf5849023d9df2617df --- /dev/null +++ b/params_shard_416.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56b7ea58e38260880d53d3bdb75a1250a3e6cb334dee735cf7961dcd618bff26 +size 31068160 diff --git a/params_shard_417.bin b/params_shard_417.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9ce8790f721f5d340a41a86c2f9a70060fba7df --- /dev/null +++ b/params_shard_417.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9501f6d29d61646ff50c3b5be5c2c7c7fa9402b416f9fb0f53dabb5406631fd5 +size 93978624 diff --git a/params_shard_418.bin b/params_shard_418.bin new file mode 100644 index 0000000000000000000000000000000000000000..9078d574bd64e57090cf0a975a2231e28c2fd38d --- /dev/null +++ b/params_shard_418.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8221d6eb4ec05ffc3c36ff4af5a7c33230f6dc2e6906b7b29b4f4d49fb9c8f5b +size 188088320 diff --git a/params_shard_419.bin b/params_shard_419.bin new file mode 100644 index 0000000000000000000000000000000000000000..ede7d251e67f4b9be066de04aef6b04debb20f09 --- /dev/null +++ b/params_shard_419.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a4bf107cf38a527e01313d9b644d96997bed75ea5027cd563c4f7290af2a40c +size 23511040 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f50acc29be4efa83c32ae97b0b94a95df2bfe7c --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d27fe179eaa5c2065ec41a8a7868b79935d8fc104707319a0bdb9a829bd8c07 +size 188088320 diff --git a/params_shard_420.bin b/params_shard_420.bin new file mode 100644 index 0000000000000000000000000000000000000000..a918b7b569f032fc80e033a11da713f42e6e22bd --- /dev/null +++ b/params_shard_420.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9fc9aea9cf8af8329eb972d3796e27c2e74c60a28009dbef17504f25d31e27 +size 33587200 diff --git a/params_shard_421.bin b/params_shard_421.bin new file mode 100644 index 0000000000000000000000000000000000000000..a50df73efaafd6ca1bcdf105e350e05aa648ae23 --- /dev/null +++ b/params_shard_421.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1eb757e47700e41deb102519518b244557aba7fe288e2a7601a99409c7a9cdb +size 26869760 diff --git a/params_shard_422.bin b/params_shard_422.bin new file mode 100644 index 0000000000000000000000000000000000000000..e88f8600e6097a45c8a1dfcb159ef2f2dad75591 --- /dev/null +++ b/params_shard_422.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4f33b2acc9f7e73cb75987fee932384b5a48ede0b4007c59278ca9858b340a +size 188088320 diff --git a/params_shard_423.bin b/params_shard_423.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a675ef9959cfc0d8c7a73274c98ee1ed48f8342 --- /dev/null +++ b/params_shard_423.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4180a80199319f70d94b372ae65c903717017c369a7aaca3c98c161bfa2b1ea5 +size 23511040 diff --git a/params_shard_424.bin b/params_shard_424.bin new file mode 100644 index 0000000000000000000000000000000000000000..a432e0c20293c4c844bbfa724d60e38d356e4934 --- /dev/null +++ b/params_shard_424.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eeffbcd9c2693bd98e2f7e3863c835b3385977d2408b35457a330d7d339803e +size 33587200 diff --git a/params_shard_425.bin b/params_shard_425.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b16a529de3f6f4e371d4e54f6ddb67c4109c825 --- /dev/null +++ b/params_shard_425.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1733174efe62c134c10c8084caf0184a5983963232e1dbb00730ead473035db2 +size 26869760 diff --git a/params_shard_426.bin b/params_shard_426.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4481d316bff8d9bb010bd9af0424a5b6f4f787a --- /dev/null +++ b/params_shard_426.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3048880b688cb09849cf382fdb9204b8f41259ab647e1780c27841f56ed3d65 +size 93978624 diff --git a/params_shard_427.bin b/params_shard_427.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8044b8fcf2612fd4eb5a5f15e32809c564fafee --- /dev/null +++ b/params_shard_427.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6b4bd0a3821c4d9b99223cc6343f7b4dd752a7b3fb1b9c3787413abf42775a +size 30269440 diff --git a/params_shard_428.bin b/params_shard_428.bin new file mode 100644 index 0000000000000000000000000000000000000000..8599ee488f54004d004a0c0f16a11471b26de83a --- /dev/null +++ b/params_shard_428.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df197ff372934bf53a0e4f14cc02aa453ec7fc5afcd4b31853b302d0e5652a3 +size 93978624 diff --git a/params_shard_429.bin b/params_shard_429.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd9a090ae933106fb02aa30010f0e6193a25d424 --- /dev/null +++ b/params_shard_429.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5ae220ff21624726a2ae02ef412c5e2ac65967905ba87cc8c326b92c701a0e +size 188088320 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..865a6035bb348c61f2ea17ea880a4405f745d16e --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c3d585cd89833ae7a892d23aa36b252bb7e3f555f86d68e21ba84185400983 +size 23511040 diff --git a/params_shard_430.bin b/params_shard_430.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f24fcd13aa04255c1d701ad405341e325e81688 --- /dev/null +++ b/params_shard_430.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:addd2b8f04c0807b7d020cad3b859013e73a2c8d7ee55a90e8bb973c9b9ea6f2 +size 23511040 diff --git a/params_shard_431.bin b/params_shard_431.bin new file mode 100644 index 0000000000000000000000000000000000000000..259b9b8b5c9ff9c85210b06d72c43fa251abdf13 --- /dev/null +++ b/params_shard_431.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec40ad9277e0a6659ef138d04262b75c003882007706a01d12bf9e857be3e787 +size 33587200 diff --git a/params_shard_432.bin b/params_shard_432.bin new file mode 100644 index 0000000000000000000000000000000000000000..e200d620bd735c9544eaa05ec97275a404fe3c02 --- /dev/null +++ b/params_shard_432.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34b425ad56c5ce986d275bbc683f42e2b751f8126a08843f037db51fc023660 +size 26869760 diff --git a/params_shard_433.bin b/params_shard_433.bin new file mode 100644 index 0000000000000000000000000000000000000000..03cfae3176d6f4fb51d1120c9670b08b19b6bdcc --- /dev/null +++ b/params_shard_433.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dff6dd3ef5f2ebe14553d2a2dbd5738bffe0712da433da2208e2f4f9114dff0 +size 93978624 diff --git a/params_shard_434.bin b/params_shard_434.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ed61ccc3ea59f55b65ddd77cb6ffa13754f7126 --- /dev/null +++ b/params_shard_434.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8986ce604c0c341ea0fc72ffecfaad2306810f7d739c95d462b12004b1a0d2f8 +size 31117312 diff --git a/params_shard_435.bin b/params_shard_435.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc6073838d7e9a87eb511d59277dbce0aa540451 --- /dev/null +++ b/params_shard_435.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7f49a350fe7954e8c161e14e985580e150ace069d6d6f0c662948727afe4326 +size 188088320 diff --git a/params_shard_436.bin b/params_shard_436.bin new file mode 100644 index 0000000000000000000000000000000000000000..486e13313d949d5423648253dcccd2d9d79f3724 --- /dev/null +++ b/params_shard_436.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0819c8ede4c977776de485a207f41d531224f65a67c76d51dafeae3b3df66b74 +size 23511040 diff --git a/params_shard_437.bin b/params_shard_437.bin new file mode 100644 index 0000000000000000000000000000000000000000..10bf4fef2096cf03de94b48d4bfe9d4e0a1c83cf --- /dev/null +++ b/params_shard_437.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c231b2a530ce626fb22e4fba6b3db12963a67637e19546720a4be1c214f30bf4 +size 33587200 diff --git a/params_shard_438.bin b/params_shard_438.bin new file mode 100644 index 0000000000000000000000000000000000000000..b99baf4ac3b00c30b2a5bc52791586a0b4c7c27a --- /dev/null +++ b/params_shard_438.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86ac73ba934a6cb8a6e01d6c51e61b29b5baad8f375da10176fbc2d100391e0c +size 26869760 diff --git a/params_shard_439.bin b/params_shard_439.bin new file mode 100644 index 0000000000000000000000000000000000000000..bc70ba847bdbda43fe253827bb6c5f731acdb2bf --- /dev/null +++ b/params_shard_439.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ac32daadd74384124bba8298c27baaa88ec2117a1b7bf95b1618ddd1456d11 +size 33587200 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..36e77514ccafb07594e85adccbc6024b152b50d4 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c290a20b4df6fce0ec3fd9c5598794d219697add2e49e071b3be9b189c54b069 +size 33587200 diff --git a/params_shard_440.bin b/params_shard_440.bin new file mode 100644 index 0000000000000000000000000000000000000000..652ff08d49f0e0beaf40150d3263b0b1f25d4c2a --- /dev/null +++ b/params_shard_440.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba2c718f4594167d1f12eeaf2959286b5d77a1340090a0fa89859daaada3a68 +size 26869760 diff --git a/params_shard_441.bin b/params_shard_441.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9c3d12d4477360a1495552180956a575f5b1cc2 --- /dev/null +++ b/params_shard_441.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66658227aafdf082b45501018c75a8d4a14f735af7399294ac77e59c0fa01792 +size 93978624 diff --git a/params_shard_442.bin b/params_shard_442.bin new file mode 100644 index 0000000000000000000000000000000000000000..acae12385e124696b84491b191d989dab5d156ee --- /dev/null +++ b/params_shard_442.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a8c6534e128ff7ba2ef593235db3cdc3c19bd8919ed8d3d5a11312129e88ca +size 26894336 diff --git a/params_shard_443.bin b/params_shard_443.bin new file mode 100644 index 0000000000000000000000000000000000000000..4fdc0628d139225d40b75b3776ba2e14a6656c36 --- /dev/null +++ b/params_shard_443.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71f3bdf5c3680a29f490153cf3deb570fb455f86096cc6469c196232398013c +size 188088320 diff --git a/params_shard_444.bin b/params_shard_444.bin new file mode 100644 index 0000000000000000000000000000000000000000..c774b2fe1db961aee4c671d5a615908f17da86f5 --- /dev/null +++ b/params_shard_444.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01bb76d598cf5b480fe55b43c869dff564a898da8defdd804c5beddd353cb197 +size 23511040 diff --git a/params_shard_445.bin b/params_shard_445.bin new file mode 100644 index 0000000000000000000000000000000000000000..7db5c4b09976b90300aa998d820ff3e0a1600532 --- /dev/null +++ b/params_shard_445.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52455be7dbed2dcca29b543370db36a17d70d6f7ee060ad538c5a7e013437e3 +size 93978624 diff --git a/params_shard_446.bin b/params_shard_446.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f9f896191b8e671f3db0cf3ead4218de6439611 --- /dev/null +++ b/params_shard_446.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77016f7d02e37ee8127d91a980e52c3135c028471bf75cdbd2c24e7027950335 +size 188088320 diff --git a/params_shard_447.bin b/params_shard_447.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0887490c233cbe345dcacc35a134d93574ed3fe --- /dev/null +++ b/params_shard_447.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d88cc9c238a79bce48ad12dd8f1f3cd895d5395a408213d0e946b0e7418991b5 +size 23511040 diff --git a/params_shard_448.bin b/params_shard_448.bin new file mode 100644 index 0000000000000000000000000000000000000000..e67300a19f658dd98009ad22c12101aa84689b7a --- /dev/null +++ b/params_shard_448.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151caea94806b99c39b03b9bcf7f6d511f6c9b2ef26c9716c78615cce8d52294 +size 33587200 diff --git a/params_shard_449.bin b/params_shard_449.bin new file mode 100644 index 0000000000000000000000000000000000000000..f857b684d90facf4a27f5e4cfdaf335513048bf5 --- /dev/null +++ b/params_shard_449.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7091bfd29aee0d10896f0716d31337ffe369b739607296b5cce59ebe32f931a8 +size 26869760 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..f0d3f1ee738a6aa9dcb38546db9bf8ba2a4f3901 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a24f0e02886f62b80d6225874689ee661062ac8400f885fb9a32e4f8a58f89d3 +size 31100928 diff --git a/params_shard_450.bin b/params_shard_450.bin new file mode 100644 index 0000000000000000000000000000000000000000..8dd52f362fb4f10db4b52674ed595e94c2849654 --- /dev/null +++ b/params_shard_450.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a876d7a34eb3473c044367ae4b950d324c1c2203a8343f4aa6a7002fee8bfd6 +size 93978624 diff --git a/params_shard_451.bin b/params_shard_451.bin new file mode 100644 index 0000000000000000000000000000000000000000..1767cd661ef8193c013130ae632b2ccaa2ffca70 --- /dev/null +++ b/params_shard_451.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9d731b8daab03227b933085d89eaba0d79093f0fd5ff027678da7b526495e61 +size 31100928 diff --git a/params_shard_452.bin b/params_shard_452.bin new file mode 100644 index 0000000000000000000000000000000000000000..806e4bea2f62149978f1daa2a6cc5fefa94648b5 --- /dev/null +++ b/params_shard_452.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f66e94c3b0f9aa9f982ce08b840a620f3d11dda24772b838e7309cd2e32a19f8 +size 33587200 diff --git a/params_shard_453.bin b/params_shard_453.bin new file mode 100644 index 0000000000000000000000000000000000000000..7e9adbe9ed2801eaec367b3129b19a0f0a28981a --- /dev/null +++ b/params_shard_453.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc639a9ea36a85796e8daa06ca82ace331bdf7538ece1af8fb2919c8c48d8d6 +size 26869760 diff --git a/params_shard_454.bin b/params_shard_454.bin new file mode 100644 index 0000000000000000000000000000000000000000..691ac4f53fcccf5d1e88e5383611afcf9a7012f4 --- /dev/null +++ b/params_shard_454.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef75696dc689aec71d13677fac67cc5e27ded338eb59d7293748f6a1257db517 +size 19304448 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..702bc25609e9e86cb52e208e94c0dcf52599b4ab --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0837638993dfd284a6cb5605a0d7ee001d69e7c78bae8509ab76c1748db1b671 +size 31068160 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..7bc8a2705ee81f36a64a99d9937a75ac38b1c1d2 --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c954954238d14e759de02d545c09ca0d154ed49e9f27ec7a125051cc7357978 +size 33587200 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..c1bb4b7717f59b645c5736568050b3807ea6e04b --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa1a4f68db902c9e78d363b1d8c40df4b89f1954798e8a05567062ee29614140 +size 26869760 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..69c323e283db47bd1a37c705dd22100208cac0c0 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f62595e7b0ba5c489fb52195779b5a12a520f5f11da94fcd565c136686e729a +size 93978624 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..6c5a242c6c2714437f55a6c8d61e9d34c5723b11 --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20330dc5f6f5a050fae1a7adb328c0b2808dcd61facbb601299ce9a7b026e4f1 +size 188088320 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..cae5375f7602df8fe86c86fd8ae3cc0cde5becca --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b43f001611015aa6b938b361bb4e3127200d63af6ec1950e9f8e647917db96 +size 188088320 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..be8c53b6e5bfa6ab1f30690e0b49400f1a203b65 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfca36999744fe72d373a43c7513423509114c0525013aa8dce014953fe6ec55 +size 23511040 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5c3bef30ea58c59f3409219a2eeaec046ac5299 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cfcbc11108276d900df488a38a2cdd1ef1acbf35bdedba6b002ac95b007f33f +size 93978624 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..b2f2e0d4f34de0ab09e14adb0122dbb4d3c5cfd7 --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2e94fd62df2ab1be50d5ca36902799fe3ab8f5b2e68112b3b7341351d13da0 +size 22712320 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..e24fe05375738f0aab5d089055cc5a412827c7be --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1648303053b9fc8b3e4e360d8996fd510fe098968e3878c16f31b7b8c28f1db +size 188088320 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..6aed16a93f59372a95b97e519fd330b4ffcddc9e --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cb9b520536afa174f8dc4e415045a384ed8d3a5ee5337e991abe41183538c56 +size 23511040 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..ae9bfd245f379d21d1343d4a8e5b42997ab2c819 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3035293792f3da24d81110d2b561276b0f210e373e19a08311b1fb12df7f55c1 +size 93978624 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8aa2177cba5b9e50ee1b518d87bcae06210f89e --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41dbcf0c6a07173c0321373dd28c89efedbf2f3b622f8edbf30e7fb8db934b79 +size 188088320 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d2c72bfdb16a1bcb9593728346829c3999d6b45 --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd6c1e0cae3745ad79a377b70f7a6d6fcb2f3c83888ba285dce064e51521b6f +size 23511040 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..ffc39b67ec7eff621cec30d1873827a4c9c09c5b --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbeb9bf6a76c33da471e3c7b18c1d069cec743b21225ea40a9e51a8a1535ca9 +size 33587200 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..a1738849f40aa174e92ff56e2f4f67e1e093a709 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdcef0a89bbcdb941149f6c9b14813468bfd39e04ff5d11347dbf168289d5af5 +size 23511040 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..865367571b66e7ce92523767ee9893ebbaeaf4e7 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c801a86bbe97fb410f62df7afa2964266cd0d23e17c77b51d1e52b1707d5863a +size 26869760 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ab1008ac4d0fa730a6c134d239250d57cbe36bd --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c174f4fb6acf83703094d56bb0d4a4af1e29b8f3fafca4737ccd5df06393e3d +size 93978624 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..bc4c8c8e3d2b4497c527e4998dce2e7e047ff64a --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec06e1f9c42f9b12d61602a2bf9ed84b3a285f97d9dec257b9a8f3f364ef6ef +size 31100928 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b2cfcf7f853a1327d90522fba43c17ae5e49648 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aedb7f082dcaa9add981f932db4bcad303a9454fa2cac075bab98fb02b88122b +size 188088320 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..e561946abc1d10e559f298e70b3bb080305cdfe7 --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b0d4223126423e76f4c9884c21beee96371f68809482e69868d7d5a14991e4 +size 23511040 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..a467980d3e1ae9a3f1aa7df87b5d3321501ec995 --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e78f723c889b4554fe8aaf55b5f95f5e8894202e717cf71782809f083aa14e +size 33587200 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..a876c2c07e94b4cced1fa52035ae04f5103db402 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7313a474f908ce1b02ffc6c36919a01ce6f112ea8f33be3ec38d2be095196e4 +size 26869760 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..cf1de471bd65f554dcf90de948ef0d1c4b00b529 --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81b50b785b3646ef00c224bb4f15aa18910102142c3e11c038460ca2ecea851f +size 93978624 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..3ebef4cc3e4d056f7bdbe8940362d69e415623ac --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92022eef9f861ad874872b89178d36800a554685644f2e1216512542012f1ebd +size 188088320 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..abf7fe9c975dbd97147f4ba45fb63b176bed2466 --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa47ab68001f912b2e574d8267205b27fa5627e2996e0027527ea821fcddefde +size 23511040 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..22c04a637835bbf676537fbc183d5edd9ebe8210 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b9f91eee6909bdeeca68941272ca1f09655cd4fc888d3fe2f3bb296f88ad57 +size 33587200 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..2923e9b3a78a6578f9afac3e583a0e822f5baec6 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7f781cecde70d34277ff3d3753149cf9c0fcc99a89d82677a6974b53fe8f5e +size 33587200 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..4fa2fd439ef8e4f1cd8c03b3c02fe1390ff0442e --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde2ca49632df08c112702298ef7256ad7cc11c28d8ad3cc1d0be9e1820eaaf9 +size 31117312 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..65cc13ca3e15d8edcc3f293fafb69dfc5c98012e --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df3ea09052bfab9144977cf289fab2e91484b1b73a8502cd840d7008d096f5b +size 31068160 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..4444c4c3d436347b39cb771d748b88c4f50559b9 --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86bb4e829675973bfa793cad6727093e423bd96f612751ab3e1dc73626af807d +size 93978624 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..eedacdfcedbf78210f3316e012fe694125932616 --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2008fd6c4628b56517834a094f2ff77e79244fb788980fd1c933a972d729e522 +size 188088320 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f18c7e28c1f780ded8473583ca033d2c58372ab --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662ccacc0551307bda61d475add050766d24ef4067edf40487dc5818f9838fa0 +size 23511040 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d159b052cecbe2a31b9c458657a92d0fb2acc46 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf5dc5716516482e0d7f46016d5002953a573896dd65870d29faf7ead2e2189 +size 33587200 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..2cada0fb7c5f4678100c5e441553c48227630d51 --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9361e87d1d7b4220cc0928860f4569ca76e11474b8165a2fcb16b26361709c6 +size 26869760 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..234eaa8ed8089af36cdeb7d4e652f57acfc9c6aa --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57c45578e581a01492fb1826d303c6d8460c3202b9b84244af2c8ba8cd4778c +size 188088320 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..13bb27949fd12aff3e2cf126faac47ba73c525d2 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf391b0183ede1a7f0a469452e31597cfdbffd46ea6e854158f67ad4b1833ce +size 23511040 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..5969838e1654b725363d773d7dbf2d1c8cc93d69 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1868343872c7dfbb6e4c9aa46a5c7c452ef636c0457fb6c069e1b51bcc6ac59e +size 26869760 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..45df835b95b14c99223a27643dc5dfa28dd39df2 --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16496216f12029d536a41713efea84b53850c6adb784a24d1b68342ee8dc5faf +size 33587200 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..c9cd156a05a446cdabcfb083b8a64fa80114b268 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82af93e560319d96b7999578c338c5282f5ddc223a621952b889ca9fdf81b495 +size 26869760 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..d05f1ff9d57f71e06940487a913a0180d298bb47 --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4210ebe36785b2a39cb20f03a5a9e60de5d35cf7cd1d873c21e5147c9b9efb79 +size 93978624 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f5bf6251aea42995b20b54dec853072900d2bba --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb5b3c74e05283b654b3e234522be8c1d110a6c0c46625e933b1b88f7398509 +size 30269440 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..09c28afa5f32b05af70c8eba3fda3f58b4381f19 --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddbdc97cf7e47ea3f859e3c42243348ac2212d17ca315344302635c7bf60174 +size 93978624 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce20c29e3312b1cedbb11317c32d7859584152a7 --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef39559ffbba34ba015994ab573ee9c1f07de749dae2b7ffbcd17b4d9fa57f00 +size 188088320 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..c91d521473cbf9e835a385615a9f077768b4bfc6 --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d93c17ab3f952c454f1cd1d6e193831161e63a17f2ad945b620151ddc9910b +size 23511040 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..37698f02ce57e4e4aef16c5a340e79a29fa2e3c9 --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d137eb6a530476eb06016c60628874e1ed8ca8f855b1244cd597a97190a70147 +size 33587200 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..1483df3213e61dc64df38c0e83264a52d759a816 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9f9a0d4ee9fb64ef595251a1f757f7f97ab981797e9c6be1e8c3a299e470f5 +size 26869760 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..594ab00528e0447e82dcd5579f9b20eb319f1164 --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b4d01d5b131baf474d24f80024a9e01ad5e144319fc82ba1a8109c3c8cf92f +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..2f1f912a902e865e930a4cb0ca4b1b6d195797a8 --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1e78ca2112ea02ea8d9f6dcce788ca139b4a230ddd45bfc17c74c909cd36bf +size 31117312 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..c2058c9642f0eb24da16d75d57d54587ec9e4a39 --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a06641dc1171ae5f86675f00b8c7a2c4e1862770009aff92c8a0d0008bfbf29 +size 188088320 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..a04ddcc3797e86b1bcdab7ce02d307ebb2ec2a36 --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd567ce9b80d761cfbca143cfc0710714d75c96662f06bc932c0dd58c565a50 +size 23511040 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ce8193400d54046dcd5a5db3c4f81bcfda4a742 --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ea21e302bc7fe6ba2d0abde735d45da5bab9984495e69fb859d3454c96bbac +size 33587200 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..0fc1f4d2242d7f094dcb0cddf79bec6a053fd29c --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa832486961f73aad09157d663fd889067bc26384791e53647fa8aa3a7bbdff5 +size 26869760 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac9b69f913c4e921be7eb921642f0154f98bb3e7 --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb4bb59eeed7bfffdab75e921ed7c0b6c54c39e0b8a7c74900d7f1510ea362a +size 33587200 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..80ead607974a509071ab3ac44ff21b4663f0b411 --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f27be9b23a3044bea965d62c29b43314d5901d90572665d7e2ca2a19cf333ad +size 26869760 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..4161eb305bf208d9891e34793a3d73312e976a51 --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b2d915374955bc046b3b5de145873046eb602de3f923a4e9628f0826007bce +size 93978624 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..faa6edde53a624abd36e45769aa524d99bccd0e9 --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5854b6d445ebe0b5707e09bdeafc66e911a9dbd26dfd4fee99c503def82167bc +size 26894336 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..4baa8427cf6d54170e93706d2a97a81b4d9d8e69 --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:124f731f754b36bc333b9da8a0138b3ad831250c5ac2ad3121ffecef7d6d71d8 +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 +}