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..e29075ca09463d4eeb55ce4a90ecb3ff0c6e2f66 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 --- + +4-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..d9e7e08f5c8e277065c653a7c72987d064f55208 --- /dev/null +++ b/config.json @@ -0,0 +1,5 @@ +{ + "quantization_config": { + "bits": 4 + } +} diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..8523ce61474912f9088b3b62992a532220f5c104 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,11583 @@ +{ + "metadata": { + "ParamSize": 805, + "ParamBytes": 36381212672.0, + "BitsPerParam": 3.4891900844756822 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 525336576, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 1024, + 128256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 525336576, + "byteOffset": 0 + } + ], + "md5sum": "3b0091e9675cc30ddb562de5cb1cab5e" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.78.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "3a43a86822c5e49eaf8595148ddfdc34" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.78.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "69e0fdab069fb773fedddb29fb22b68c" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.79.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2d46c9826b05e7a1a0e279024349ef76" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b8b996ff6926b0d0dece216fae944db0" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 31145984, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 64, + 128256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16416768, + "byteOffset": 0 + }, + { + "name": "model.layers.78.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 16416768 + }, + { + "name": "model.layers.78.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 16433152 + }, + { + "name": "model.layers.78.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 20103168 + }, + { + "name": "model.layers.78.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27443200 + }, + { + "name": "model.layers.79.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27459584 + }, + { + "name": "model.layers.79.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27475968 + } + ], + "md5sum": "acbf98c398c7c7c6a7d589798af9a02e" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.79.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "03e8049c5efae78d74a6873212c47400" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.79.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b2fee82bc2d3464527e6955701c04db5" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 525336576, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 128256, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 525336576, + "byteOffset": 0 + } + ], + "md5sum": "3ed7d852262933b734b9bba319aebb07" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c27430a98147150a548ee3cb6501fbdf" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "dec9d07681f193e5710ae63173651aa0" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 29835264, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.79.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.79.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.79.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.norm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 128256, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16416768, + "byteOffset": 9732096 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26148864 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26165248 + } + ], + "md5sum": "485028e71938369726372cc7236b8193" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d4cc8135ba9815fe19f8b4123848cfe6" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a381a980eb9aa939ef1cc8ac02e9b9cb" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b8d402908c98802d22bf64726dd267c3" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a2463d47f75b41e1ec85296ed8c639ed" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7c1421417fbb514c97634adb9b0bb3a5" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b69df290d68d83a27dab3033d8595761" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "cd3db516ab1e6a0b7d147b79c4644223" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a87c267bd82f65c3049189d2de58e550" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "036c34cfcc4488495405970d6f57b055" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e5d9aeb590424acdd5d7a655ce9a970e" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7347305b0555b91f4204c548410439c9" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9c56806f024ffb8d107cbca09ee69e3b" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1ef97c8e65548bff191cefa15759d527" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "eb8ac00a7f5346a97dfa7a372b277976" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9661dbc7c82ccfa14168279e0ce6cfc8" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5e055ee66ae61e2d7322b296dd2665a5" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f92174821315fec7ff46b7f6fb78baa8" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bce36c27c70d0769ceb90af67446de1e" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "541b711de627ec9b5a2e57ef5ee6d76e" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "b9ac5d48eff64e9479b98a080a101a1e" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "49fdd1a0ba5fc5b19880417815e9d6da" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f0883e5acd98e70b7ce891516ddd9286" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bc26b1f52db76cda3ecd3978d2ddc0ef" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d6fd046d58bcb4a7d2ba5066a445bea4" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "175c740c5eac48f9c9284411b351769c" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d1056b8baba677309d79dbf195fb3e54" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "694c89aa4961a35a721b12d02c81ecc0" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c8d51bb1f739bca3ab04b48850064948" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c1cb588ff6ce5768225fddde59b9f661" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "74f99c1bbe2ec0c1af1954e44d64b4ad" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 32833536, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 23117824 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 30457856 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 31768576 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 32817152 + } + ], + "md5sum": "67c64e9912a8c17fbfb90b6eed268cd6" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a85aaa64f233af4409ad4a7a65b0734c" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "52d022b7f63ce5fc87b3dec3a7433288" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b87b6c72703a03c76e4b4356970943ea" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "01880e9dac55abe325c0a5df33db3544" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0fe6182f6b9d7ad46cfcfa156643a180" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0886b0505cb2808ef5896fb170087560" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0b3aa94305646f5cd1997362ab4f73dc" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 28147712, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11042816 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11059200 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 11075584 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 14745600 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22085632 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 22102016 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 23412736 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24461312 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24477696 + } + ], + "md5sum": "a69b1a00e0f03670dc8220472e6f3a2d" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "2eb895ac057e6e8fe293a678b7cb8fa7" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b17f9a9fa8e7fd1797c06c179bfcd727" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6ae3460edfd8f0117090f9dba1f17bac" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1172c849d7202f3c134613fd219d0138" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "828357220a73cf0c40931fe5ffff7250" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ed046ccd9a0beade388797eec274b253" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "44e4b485206e24956754b605be86977a" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "cae21301a85c2384b6df3d66c3589a74" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "bbf46a89c4230c48976ef5ee1282bd19" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "04aa0add0f01ea34883763fb0d34210d" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6ce2eb2b5f3e3f3ace4a5e75ffdd2b4c" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "1ca3b9357fb19f8ff54b085236cc140c" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ca2d034efb249fc7b9abba04d959ce9e" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "81d48e1e95ad28bd9d66c4ac215a534e" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5a89c14712f3d1e0195a396f7d3a6c13" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c061b36e640a648713bd13b7c1c7e135" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e9c1bf5bb12e5723c24c5871b3f59e1b" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "10e6a87d1d87df654e3eb837d38cc46f" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "4c63435584c97a2ae0700824ebdcea92" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "652b557091be2132ace13fbe7be14cd8" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4310066876c6744c756f9dd45d0aaa5b" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8516eccbe851c7f3919002979c68dcc7" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "67a9a5d6171b183c241e5a46e6e34912" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a45b6d0301e3b0d7e04a93eff939aa19" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2cd4c12e41fb4a0e157c29c1ea22880f" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "55b47ae04aa85e82e0cf489e7bd8f773" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bf1296bd3b4ecdd56320b015fe0e362b" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 32817152, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 25477120 + } + ], + "md5sum": "bf322f6875acb082b4b0d624d1bfc704" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "04a170dc8f130c80b8bb764e83c03849" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9b7933859fc129c7f04ed8a37a5bb3ac" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "80d9675e1682207de30d286b168d4da6" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c54b8e34eb619cc2709fb3b195cba96b" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ae3ba30a3f2b0986101d7850c297b43a" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "46408d269c5de476d67e677b3c89c956" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "719d85a8ed48b5bee9004b61b338275f" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "593142af28b802520ab5d29217eeebc1" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ab4297fd143cd96b14255be05f4e5716" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c0e4344ec700186a1e6559da04397e1c" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 29196288, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 1310720 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2375680 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2392064 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2408448 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6078464 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13418496 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 13434880 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 14745600 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15794176 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 15810560 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 19480576 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26820608 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 26836992 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 28147712 + } + ], + "md5sum": "57e78e21784a0a17ce584773995012af" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "86d953e8543a95ac19950e5e9caa51df" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c88ba27a47a309f8ff7e74bd9bab63ce" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "3431f69ec8cbdc5fc3d645e354a04380" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "749ed7fd8fa09d109ac71a3af4643651" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f0f444c81f4d0c8288e09001e3b2ccda" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "aeb555ad521cc355cab33cfd49b774a1" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "bb17f34ba42366ccffc4cba7b1c530b7" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "3f3fc27fd133177eb52081abbeb963c1" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b4615e6816db6a422151ead0fe98a707" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 30490624, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9715712 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13402112 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 13418496 + }, + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 17088512 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 24444928 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 25755648 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26804224 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26820608 + } + ], + "md5sum": "eb0bafef76c8f18029be3a589cca368c" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "3e47b974cf7990f3fbc90abbeb1e73a2" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b8422de621108f2b545bf180452436b1" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9c1d45f66b3c2cfd48730d2340d836f0" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3aa2f8851b9a21e8089990b789053fa5" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "74404dfcf00c246456f2333d9eb0c768" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "95d8cd3fa7e0f14426b1ba90c90503b0" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e266f5501698a5542a59ac8a3ae6853a" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "7dfac806010d7a40f395765919ca4370" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "e73ebc2b41247de3f421ffcb4e21aeb8" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "88ab8ba685f09ab7d0c05272d05f76e3" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3ea76549bb97e5a8f9e20ab5629fd4e4" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "cb1d511719e48fa0cc1050e9cb9fc7bc" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "bcb5389c1781c3ea1c3d316164be1c23" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "49694811695f6d8d07acbf745fbbf6d9" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f8c72d8a52ee6dd7c28d259edb3dd52a" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "617411c28b1acd2064c2bf597794561a" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b0b5e9501e66d4a443a580d958ec912a" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c7d5575751a1f8e380705706b7da5d32" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "b6e8805c15a404af36fd8afebffab72c" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fa879caf8971c0880e1bae3193383efe" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d03b3ec131e14dbe56cc23ea829607ec" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b81d88c3e11ada987ba32a714fda2e48" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "ab8ae63b5632f24088925c9b7869adc8" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7e628005783bd068c4de7e7d17becdc2" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bdfcd3062d1772bb96a2f66d3514736d" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4b622b288dce74f0f4ac6ec54eff7ee7" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "f92a2025c0dc7786462649299a023b92" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 32817152, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 25477120 + } + ], + "md5sum": "e44688afe376be68497776234b712e3b" + }, + { + "dataPath": "params_shard_128.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "960d1bf66f4e8ed617ebe28dcd77e53b" + }, + { + "dataPath": "params_shard_129.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c805eeac496fee381e4145ce21ef3ff3" + }, + { + "dataPath": "params_shard_130.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "03be1da585b197e663765e0715e2ca3a" + }, + { + "dataPath": "params_shard_131.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9267c9bf1abc0cb18bb365290055abf7" + }, + { + "dataPath": "params_shard_132.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "cd8d7f411d046032c91fa27ac069ce20" + }, + { + "dataPath": "params_shard_133.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ce094114dff3917f2662e2113c27ef5c" + }, + { + "dataPath": "params_shard_134.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "02dcce3f6f85e41e3f8912a494626a7a" + }, + { + "dataPath": "params_shard_135.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d1b4d67c3e1719c09eabf75ac547014f" + }, + { + "dataPath": "params_shard_136.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c715844daca04d67bbdb5cdcadc31dfa" + }, + { + "dataPath": "params_shard_137.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "23a011402cbe0b9919799a67d31c8a63" + }, + { + "dataPath": "params_shard_138.bin", + "format": "raw-shard", + "nbytes": 29196288, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 0 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 1310720 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2375680 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2392064 + }, + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2408448 + }, + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6078464 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13418496 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 13434880 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 14745600 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15794176 + }, + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 15810560 + }, + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 19480576 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26820608 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 26836992 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 28147712 + } + ], + "md5sum": "c76bd56cf6f7a922163a3e8a17d92484" + }, + { + "dataPath": "params_shard_139.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b8ab4622c891d23c2f2aaa06790983f0" + }, + { + "dataPath": "params_shard_140.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4b696222d19874aeb236b767c20c6f80" + }, + { + "dataPath": "params_shard_141.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7764d3a5d6e9687402f84e5d18bea54b" + }, + { + "dataPath": "params_shard_142.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7665c5653cf92bd3f1e2804780267fc2" + }, + { + "dataPath": "params_shard_143.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4cfc9567b3cacf290736a5cabbd66d9e" + }, + { + "dataPath": "params_shard_144.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "46b83ddea07b1bb79b4944a2874c8799" + }, + { + "dataPath": "params_shard_145.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a46473baf0590771f06d727e81161763" + }, + { + "dataPath": "params_shard_146.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a6f8f9c301c99ba912ea0844d942f5a5" + }, + { + "dataPath": "params_shard_147.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e3e8857cb9a936ce73fdf61c8f20e3e2" + }, + { + "dataPath": "params_shard_148.bin", + "format": "raw-shard", + "nbytes": 30490624, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9715712 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13402112 + }, + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 13418496 + }, + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 17088512 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 24444928 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 25755648 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26804224 + }, + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26820608 + } + ], + "md5sum": "637fb80c9fb3b166caf9d8b333243d50" + }, + { + "dataPath": "params_shard_149.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a70afba27105890e8fd3a62f711756ee" + }, + { + "dataPath": "params_shard_150.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "23790761c69e6dfd71e77573dd7113d2" + }, + { + "dataPath": "params_shard_151.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "906d5ba86df0ef0a717fe909d5ab99ae" + }, + { + "dataPath": "params_shard_152.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "66d08638d6d38c979c05d818a470fda3" + }, + { + "dataPath": "params_shard_153.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f40673e186d9ff0cbb5e9124fdb13c0b" + }, + { + "dataPath": "params_shard_154.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "2d5e4c6bd231911e0d7b9ca5bb7a92d9" + }, + { + "dataPath": "params_shard_155.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7df31eb7e06f531cde96ff0d373b7579" + }, + { + "dataPath": "params_shard_156.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "573bbe510113005913a6622438662912" + }, + { + "dataPath": "params_shard_157.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "1f9f30c41fcd71553cbbdf9437d1856f" + }, + { + "dataPath": "params_shard_158.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e19c774801bfdbddd30bd4879fd5904c" + }, + { + "dataPath": "params_shard_159.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "551a2f11f7dd057879e4b97bdf5bacfa" + }, + { + "dataPath": "params_shard_160.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "389caad95e660bd195f4300828966d1b" + }, + { + "dataPath": "params_shard_161.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "2efe84dc30d56d6c803d2ead2fec8ecd" + }, + { + "dataPath": "params_shard_162.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "59704f8532bfb212f024c85108177294" + }, + { + "dataPath": "params_shard_163.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "aac9a8b8191dcc462f43a7dd3afb42c6" + }, + { + "dataPath": "params_shard_164.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.40.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "f07758ce8b2c03a29932bd384d98b49d" + }, + { + "dataPath": "params_shard_165.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c77a4ed5837c1d6d0b2f4bff5bcbde24" + }, + { + "dataPath": "params_shard_166.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "3eed40f96bec1b7dfc1b301691ff8008" + }, + { + "dataPath": "params_shard_167.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "e89770b7051eac5bb65b902e5c6e2567" + }, + { + "dataPath": "params_shard_168.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6dcac02a5e0aa661eabde1a466c076e3" + }, + { + "dataPath": "params_shard_169.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "eb025a588000721f201deec106530043" + }, + { + "dataPath": "params_shard_170.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "2a04fd19e8495cfdf0a1b37770b44d5e" + }, + { + "dataPath": "params_shard_171.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ec6e8977f9a8cb616ee6b77f23e137d8" + }, + { + "dataPath": "params_shard_172.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6b0f8d0a7f02148359fd0c4ecd086c8c" + }, + { + "dataPath": "params_shard_173.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1a6c6cd6b9a436f2be3c21c5584149ca" + }, + { + "dataPath": "params_shard_174.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8b3469d66d22889a29dc475698a47d03" + }, + { + "dataPath": "params_shard_175.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1ba3e7104f7363d26bffe17cdff05838" + }, + { + "dataPath": "params_shard_176.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "f56f3260fdc5dc4cbc127fc01d7385b6" + }, + { + "dataPath": "params_shard_177.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9c6fac4eb20ed805343425a32ee6b27d" + }, + { + "dataPath": "params_shard_178.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b18cb2b436b6375f95cc8f8f0c435e19" + }, + { + "dataPath": "params_shard_179.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "927b0dee84862a866a4f2b23262d5560" + }, + { + "dataPath": "params_shard_180.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a6178a5609c9a18b6c3f99697d161236" + }, + { + "dataPath": "params_shard_181.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fc1c3fb3409c8eda74db43e6d29d51b8" + }, + { + "dataPath": "params_shard_182.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0440764f2f8c42ce96970fc5d87f7656" + }, + { + "dataPath": "params_shard_183.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.41.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7ad76b37db7320f61509f9ee1a7d368e" + }, + { + "dataPath": "params_shard_184.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6e43cc201bcfd5bc2428647b76c90ac5" + }, + { + "dataPath": "params_shard_185.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.42.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "cbd31ecab5e96f82fc29565e290ad19f" + }, + { + "dataPath": "params_shard_186.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "543a55b18bc570dc9a4050fd69fe5f33" + }, + { + "dataPath": "params_shard_187.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.42.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "3cd1bd37e9da5fa3098c8f99c9c4e6b2" + }, + { + "dataPath": "params_shard_188.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.42.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "77e01e01a8688e9b1723bbfcd0be9b50" + }, + { + "dataPath": "params_shard_189.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.42.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "8f984e7d7823bca09d593671f91e21fc" + }, + { + "dataPath": "params_shard_190.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.43.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "1231ca8abf17abda94b59313d07dc0d6" + }, + { + "dataPath": "params_shard_191.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "fbfd73a31e499c0bd00ec90d488cb67f" + }, + { + "dataPath": "params_shard_192.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.43.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "13e4b6263c8d2e2331b49f496513deae" + }, + { + "dataPath": "params_shard_193.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.43.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d65175b971bcce4242192863afc8428b" + }, + { + "dataPath": "params_shard_194.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.44.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d8d0fb2c75f8151c0b285a7479e682ec" + }, + { + "dataPath": "params_shard_195.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0db85adc89e514a8df0427756d5043a1" + }, + { + "dataPath": "params_shard_196.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.42.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.42.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.42.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.42.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.43.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.43.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.43.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.43.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.43.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.43.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.44.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.44.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "ed8ae69ca248c3a05d1f10ea6f340599" + }, + { + "dataPath": "params_shard_197.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.44.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bae9b89fff81e05474d786545a72c8ae" + }, + { + "dataPath": "params_shard_198.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.44.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9bdc75d46c274b4c083f2f8035d7c6c0" + }, + { + "dataPath": "params_shard_199.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1807221e62856eb1c68acacf5c2bdfb7" + }, + { + "dataPath": "params_shard_200.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.45.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "cae4df133bef3fe701fb38e0cfcfdc05" + }, + { + "dataPath": "params_shard_201.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.45.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2d4883af7218040b101fb7caad8d7b2c" + }, + { + "dataPath": "params_shard_202.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9e3635672a75c7459996d45db8ad4a18" + }, + { + "dataPath": "params_shard_203.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.46.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "87d3118a132001567107ff0a97576d61" + }, + { + "dataPath": "params_shard_204.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ae637f0643db74d5d33274b8703fae4d" + }, + { + "dataPath": "params_shard_205.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.44.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.44.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.44.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.45.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.45.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.45.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.45.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.45.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.45.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.46.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.46.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "2473df2b50200702dbabf41c0c028586" + }, + { + "dataPath": "params_shard_206.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.46.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "26c5e15f4818dbd7a148e75180532ace" + }, + { + "dataPath": "params_shard_207.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.46.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "cefcac532c7f224bb93dfce7f359c8ed" + }, + { + "dataPath": "params_shard_208.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.47.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "328d1ffe6077a6f6602ff41b76683e12" + }, + { + "dataPath": "params_shard_209.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9ee4384f122488264237ae923bc0a15c" + }, + { + "dataPath": "params_shard_210.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.47.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "45dd90f8cb3585f9c17ae7b2db43ae86" + }, + { + "dataPath": "params_shard_211.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.47.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e9b485ff71aa5836f94fee1dc9c18a8f" + }, + { + "dataPath": "params_shard_212.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.48.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "064c862d24f9139ab23140602687e344" + }, + { + "dataPath": "params_shard_213.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.48.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "89571c1283d3fa41aed0cb6f89e1f937" + }, + { + "dataPath": "params_shard_214.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.48.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f2913e806491efc2e3b34fae46eb8c04" + }, + { + "dataPath": "params_shard_215.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b10714c2f8a50c57b5e6fb9f273ef23f" + }, + { + "dataPath": "params_shard_216.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.46.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.46.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.46.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.47.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.47.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.47.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.47.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.47.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.47.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.48.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.48.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.48.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.48.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "d9023ad03fec8f6197a5b6bcbcf0e6b1" + }, + { + "dataPath": "params_shard_217.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.49.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "71d2abce2344fdc42b65cfb39132c8a6" + }, + { + "dataPath": "params_shard_218.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a176f94e38aace96dd2bc7580bdb6eb3" + }, + { + "dataPath": "params_shard_219.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.49.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "62a8dfd5d24daed0c10abec0d76374d2" + }, + { + "dataPath": "params_shard_220.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.49.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4bef63b1133b375aee9acb7ab49d9ea7" + }, + { + "dataPath": "params_shard_221.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.50.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fadea87bf9ed73c094c7b60926823b5e" + }, + { + "dataPath": "params_shard_222.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d4f08f467b5a9f7c22563fadf4dbf0d5" + }, + { + "dataPath": "params_shard_223.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.50.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b5fe097e8fe79943207e1a5cb21bb40e" + }, + { + "dataPath": "params_shard_224.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "dc1a75478571df96cb3e037bbe1212da" + }, + { + "dataPath": "params_shard_225.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.48.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.49.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.49.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.49.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.49.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.49.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.49.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.50.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.50.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.50.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.50.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.50.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "06ac6cf63fa5d8d77bffbbff8e906146" + }, + { + "dataPath": "params_shard_226.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.51.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "304bb9e2924a69e34241cba3b4d58001" + }, + { + "dataPath": "params_shard_227.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.51.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d375eefc53a64179c73cd9b189c70b98" + }, + { + "dataPath": "params_shard_228.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e1b64922433283d2a166d0db3e726789" + }, + { + "dataPath": "params_shard_229.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.51.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fac18edc0bc9f765457b3e9508654abb" + }, + { + "dataPath": "params_shard_230.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.52.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "80cf444988c52b85007c761bdd5f4205" + }, + { + "dataPath": "params_shard_231.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ee54f36f87906a23f2dff3bd9fdb370c" + }, + { + "dataPath": "params_shard_232.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.52.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d3b30d52521a3064ed50207c1ed2a25c" + }, + { + "dataPath": "params_shard_233.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.52.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "265df46f079ea8d402794e4d5ad66ee9" + }, + { + "dataPath": "params_shard_234.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.53.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6411483eef97550b67cdb1d50d8822a3" + }, + { + "dataPath": "params_shard_235.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "7a1fd90e78e90b93c1a4ee05bf77cb47" + }, + { + "dataPath": "params_shard_236.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.51.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.51.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.51.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.51.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.51.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.51.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.52.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.52.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.52.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.52.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.52.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.52.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.53.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "3f92e3faf393bb023ad4e945085f454c" + }, + { + "dataPath": "params_shard_237.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.53.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bd30d0c37f08aaf09a54cc0bc8ca30b1" + }, + { + "dataPath": "params_shard_238.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.53.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6e656e80977d35a645c8e4ec96f58ab1" + }, + { + "dataPath": "params_shard_239.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.54.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fc41cb29331c0b1faba49f857315a6e7" + }, + { + "dataPath": "params_shard_240.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "80da4831f49fd014f5655524b23081c9" + }, + { + "dataPath": "params_shard_241.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.54.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bddd91d021d67d98057ab2e96d1f7b47" + }, + { + "dataPath": "params_shard_242.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.54.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "779c675a985ea72b58005d26f0a54016" + }, + { + "dataPath": "params_shard_243.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.55.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "eaec0d38b7ce8d5f0e08de55f9725f91" + }, + { + "dataPath": "params_shard_244.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "80deca43dcffcc63c9a24741a8b7561c" + }, + { + "dataPath": "params_shard_245.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.53.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.53.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.53.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.53.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.54.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.54.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.54.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.54.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.54.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.54.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.55.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.55.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "90b794782cd99f3730f4003e066f3ae3" + }, + { + "dataPath": "params_shard_246.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.55.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e8ca505294dd171b309dfd836fe0bad4" + }, + { + "dataPath": "params_shard_247.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.55.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7dd07cd823a9d00292110e981b58b148" + }, + { + "dataPath": "params_shard_248.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "33b1d1a6f03a3980e8f5b72601ca83df" + }, + { + "dataPath": "params_shard_249.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.56.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d9e138dad41f9ed36962869283342ebb" + }, + { + "dataPath": "params_shard_250.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.56.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f79e992717a1b0bf31cb1f35b0e42d8b" + }, + { + "dataPath": "params_shard_251.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.56.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c51eeab46f0b1ef206970909670ae20e" + }, + { + "dataPath": "params_shard_252.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.57.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "adaa9bc9d1034544767285b345838ff7" + }, + { + "dataPath": "params_shard_253.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5d71692e202392e2d23321f44955a44f" + }, + { + "dataPath": "params_shard_254.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.55.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.55.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.55.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.56.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.56.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.56.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.56.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.56.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.56.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.57.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.57.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "e813150ad4811b3de04a8782a38ad84f" + }, + { + "dataPath": "params_shard_255.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.57.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "ceebfd1dc69a6481570ac5d7ca9c1d3d" + }, + { + "dataPath": "params_shard_256.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.57.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fa9d980adad3432c922313fffa80931e" + }, + { + "dataPath": "params_shard_257.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.58.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "cf518f11b272fcdb86f838b81698d5db" + }, + { + "dataPath": "params_shard_258.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0b2c0c6e0744e4906e08c4b7c2b8185a" + }, + { + "dataPath": "params_shard_259.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.58.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d1ff02d99831b26dd9b60cf8a63d6a77" + }, + { + "dataPath": "params_shard_260.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.58.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2b10ce17ce662e777605abb25ac29792" + }, + { + "dataPath": "params_shard_261.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.59.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "af24534cf34b0b56b80f1b52764ff71f" + }, + { + "dataPath": "params_shard_262.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.59.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c3ffe074ba076e79f239d414c4bed5cb" + }, + { + "dataPath": "params_shard_263.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.59.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "cc33062156c5ceffadf26577376a270a" + }, + { + "dataPath": "params_shard_264.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8604a97588e59df2a75b033edb9ffe8f" + }, + { + "dataPath": "params_shard_265.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.57.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.57.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.57.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.58.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.58.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.58.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.58.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.58.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.58.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.59.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.59.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.59.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.59.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "0b04d9e8acd2f2420d4cbbe7efcdbf2c" + }, + { + "dataPath": "params_shard_266.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.60.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d96c65116e5b1c862dbf60269dee6e42" + }, + { + "dataPath": "params_shard_267.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "167409d024eabb819f3ba07a27e6615f" + }, + { + "dataPath": "params_shard_268.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.60.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b665a6c72f0a01b58f04630d27d92048" + }, + { + "dataPath": "params_shard_269.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.60.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f59fc8ca9d7fbdaeb83c2f23e6705942" + }, + { + "dataPath": "params_shard_270.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.61.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2fc4142091dce26505a1402457c038c3" + }, + { + "dataPath": "params_shard_271.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4e000e7cf9fb6bef5d82a85160f855c4" + }, + { + "dataPath": "params_shard_272.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.61.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "69702a60d3808989b566621b38bd04d2" + }, + { + "dataPath": "params_shard_273.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fc26b965d4e921c752bc3dab570f0e72" + }, + { + "dataPath": "params_shard_274.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.59.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.60.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.60.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.60.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.60.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.60.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.60.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.61.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.61.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.61.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.61.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.61.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "21e2f81cfed76e585caff2495fc8ff55" + }, + { + "dataPath": "params_shard_275.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.62.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "cac39031866c7becd4f995e8b8def826" + }, + { + "dataPath": "params_shard_276.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.62.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "3bbd01e01ee73c5d8ee492f79ca149ca" + }, + { + "dataPath": "params_shard_277.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "58eae90e703b9a2f7052c459be04b768" + }, + { + "dataPath": "params_shard_278.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.62.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a9ff11bf82a8aa8da1a7293e4f1b153c" + }, + { + "dataPath": "params_shard_279.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.63.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b46ccd85d1389523a83a790cb4e51205" + }, + { + "dataPath": "params_shard_280.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "02d4e388d5bfc59ec154bc481fa7e33c" + }, + { + "dataPath": "params_shard_281.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.63.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "59ae56cfefc786d9ffc1602cffc4d260" + }, + { + "dataPath": "params_shard_282.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.63.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "de2088a91a8c25d6117d53251df7bb54" + }, + { + "dataPath": "params_shard_283.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.64.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "22ff80d1ebb9fc9b44a3d1ccbd143d21" + }, + { + "dataPath": "params_shard_284.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0237f16740ec7a4be1bcff540b8ea646" + }, + { + "dataPath": "params_shard_285.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.62.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.62.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.62.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.62.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.62.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.62.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.63.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.63.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.63.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.63.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.63.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.63.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.64.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "135c9629d767d58fd1b76129072e1f1b" + }, + { + "dataPath": "params_shard_286.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.64.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "89b5b9adcfcb5cea39edccec30bf19f2" + }, + { + "dataPath": "params_shard_287.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.64.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "711fb4fbb804094a03874f2df3cf2b94" + }, + { + "dataPath": "params_shard_288.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.65.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "017c0207e02acd46a2e88fcb180321b7" + }, + { + "dataPath": "params_shard_289.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.65.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "167a47c1f3252f6bae5ba34428421fb1" + }, + { + "dataPath": "params_shard_290.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.65.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7824c4a4f113f51e9b682ba746bf24a1" + }, + { + "dataPath": "params_shard_291.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.65.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "81c1a830c6075622e3bf1dae64ed82f6" + }, + { + "dataPath": "params_shard_292.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.66.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e6d9fcddb82a096160b20625437a0f73" + }, + { + "dataPath": "params_shard_293.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1536fe5604e346048b6bb26f78cec79a" + }, + { + "dataPath": "params_shard_294.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.64.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.64.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.64.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.64.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.65.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.65.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.65.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.65.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.65.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.65.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.66.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.66.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "d458dc28eff767b0722d7cae8ab5e237" + }, + { + "dataPath": "params_shard_295.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.66.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "450c3600ea4d068b8b30307c8dce9f63" + }, + { + "dataPath": "params_shard_296.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.66.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "15fb8be7e986200e7118f870202bab4a" + }, + { + "dataPath": "params_shard_297.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.67.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e2585c96ff725b0ca96a68620b56b82d" + }, + { + "dataPath": "params_shard_298.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.67.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "03f20e375d326ab178cbf4b2f98d7b8c" + }, + { + "dataPath": "params_shard_299.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.67.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "bbec400a4010b7993f09691a7b22effb" + }, + { + "dataPath": "params_shard_300.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.67.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "041f2751ebee3699d6b3e5b5bbebd3b8" + }, + { + "dataPath": "params_shard_301.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.68.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6d0262df1d4ae1def9db467652d516b3" + }, + { + "dataPath": "params_shard_302.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "21e43f7a6f3896191525f04be4dccb5a" + }, + { + "dataPath": "params_shard_303.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.66.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.66.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.66.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.67.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.67.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.67.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.67.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.67.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.67.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.68.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.68.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "21dbcad32513f4a7945be531e25aadcc" + }, + { + "dataPath": "params_shard_304.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.68.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "28894f31d17ae6a9b215c5902565c62f" + }, + { + "dataPath": "params_shard_305.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.68.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "390e476a81a49f64df21b458f6c7fc33" + }, + { + "dataPath": "params_shard_306.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.69.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "612e281faced9d6a5b9aabac94fd1e2d" + }, + { + "dataPath": "params_shard_307.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.69.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0a9a27b3fc39b5c877c96c453b0d196c" + }, + { + "dataPath": "params_shard_308.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.69.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e8841fc6785fc994ffd05eecf00d13c1" + }, + { + "dataPath": "params_shard_309.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.69.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c7180874f4e706ff05c8e9bb4726dbfd" + }, + { + "dataPath": "params_shard_310.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.70.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "680d2fd473481c8fb0e809ac93b1e9c7" + }, + { + "dataPath": "params_shard_311.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.70.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3c893b77caba64657f295b5eaee6cfed" + }, + { + "dataPath": "params_shard_312.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7484055d86afe2b074f04e84da3ec6df" + }, + { + "dataPath": "params_shard_313.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "df34d81702ec731e92746ce1820de897" + }, + { + "dataPath": "params_shard_314.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.68.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.68.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.68.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.69.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.69.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.69.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.69.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.69.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.69.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.70.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.70.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "b4d5b4df753f68dcaa8ec9843316d975" + }, + { + "dataPath": "params_shard_315.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "da5216360a72df46cd6155c73337a747" + }, + { + "dataPath": "params_shard_316.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7c2d5da4bbe7eda742ddb2f573fa2c40" + }, + { + "dataPath": "params_shard_317.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ee64a474e589e941353dcf87045ba07e" + }, + { + "dataPath": "params_shard_318.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "aa01a4c73ba55e5d433c5d25266e2f01" + }, + { + "dataPath": "params_shard_319.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f0184d199be0635cab5c751e213e2495" + }, + { + "dataPath": "params_shard_320.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "73416d37286691292aaa3d12e11495d1" + }, + { + "dataPath": "params_shard_321.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4b1e7202a87565f5364816000aa51a9b" + }, + { + "dataPath": "params_shard_322.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1dd7c213f5ea778e97576ac20d5f4565" + }, + { + "dataPath": "params_shard_323.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.70.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2fb0f31511cbdbe910c5f7610b79c267" + }, + { + "dataPath": "params_shard_324.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c24156e537a7ebb93886b5c51e3acc49" + }, + { + "dataPath": "params_shard_325.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25477120 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26787840 + }, + { + "name": "model.layers.70.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27836416 + }, + { + "name": "model.layers.70.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "9773e2b9ed4bb2ea0eb3a1470d9e8a79" + }, + { + "dataPath": "params_shard_326.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.71.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fe0019cf2e681e74f4b19f0ec02c9530" + }, + { + "dataPath": "params_shard_327.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.71.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "73c350a56c789b8f8ed25e6d4cd8ae66" + }, + { + "dataPath": "params_shard_328.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.71.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c84f8766b72133950035b954c9080280" + }, + { + "dataPath": "params_shard_329.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.71.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "335cf6a5cac9bdb84193f14ee985459f" + }, + { + "dataPath": "params_shard_330.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.72.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7dd0bc02024572dec83f5802e2620af4" + }, + { + "dataPath": "params_shard_331.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.72.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "cb2f71ea2e737278cb3ea2bf2f95e85d" + }, + { + "dataPath": "params_shard_332.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.72.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "09f565f18f053bf0508dfa7dee5983a2" + }, + { + "dataPath": "params_shard_333.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.72.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "45528089266e197dd814a8a09f805d85" + }, + { + "dataPath": "params_shard_334.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.70.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.71.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.71.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.71.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.71.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.71.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.71.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.72.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.72.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.72.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.72.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.72.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "1043dd27a358462a1158316bf574dcca" + }, + { + "dataPath": "params_shard_335.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.73.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "560d68a35d4e367f257e8f5d24872123" + }, + { + "dataPath": "params_shard_336.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.73.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ae76d6ff5454fded94080a864211a7c6" + }, + { + "dataPath": "params_shard_337.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.73.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a99188e957ac7ba56eda367505ca0fe7" + }, + { + "dataPath": "params_shard_338.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.73.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b6ea0db7f7bc8aa1c06219322f493514" + }, + { + "dataPath": "params_shard_339.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.74.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9f895ef8bc4d3a5dd932b28e6b501324" + }, + { + "dataPath": "params_shard_340.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.74.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "fd1552a80501ed75524ca7c6233d8421" + }, + { + "dataPath": "params_shard_341.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.74.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c2910a28e30e90f2a901a3103968a166" + }, + { + "dataPath": "params_shard_342.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.74.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fb502e189cb7b3622e2bd51d67182c31" + }, + { + "dataPath": "params_shard_343.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.75.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "72e8a483859990d3a1c841b5c6b08aa4" + }, + { + "dataPath": "params_shard_344.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "996d6e0683540c286b4bf901e9f65742" + }, + { + "dataPath": "params_shard_345.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.72.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.73.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.73.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.73.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.73.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.73.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.73.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.74.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.74.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.74.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.74.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.74.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.74.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.75.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "55b10904b2d1819a6315f99260750dd9" + }, + { + "dataPath": "params_shard_346.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.75.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "44b7a467c94cc61675b919304c64b1dc" + }, + { + "dataPath": "params_shard_347.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.75.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c00796fbfabe7fe5a1ccaef618a43844" + }, + { + "dataPath": "params_shard_348.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.76.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d577415c5f064c0b73d42f9684c7a4b5" + }, + { + "dataPath": "params_shard_349.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.76.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "77d7ac992f44fd96a6ada9f812084ad1" + }, + { + "dataPath": "params_shard_350.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.76.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "548df139908140d022abc4549ab93c37" + }, + { + "dataPath": "params_shard_351.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.76.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0f3ce088e5729275dfd73fb191b98034" + }, + { + "dataPath": "params_shard_352.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.77.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "62352c6e2a23e9661cb3a734130ea9ea" + }, + { + "dataPath": "params_shard_353.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e63b5c7add250333122ae259d292c679" + }, + { + "dataPath": "params_shard_354.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.75.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.75.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.75.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.75.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.76.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.76.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.76.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.76.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.76.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.76.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.77.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.77.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "d31518222d559c7c411fb4491eceddc2" + }, + { + "dataPath": "params_shard_355.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.77.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bccb227f26b7a09aab7c9ab228954d48" + }, + { + "dataPath": "params_shard_356.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.77.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b953c506c0b7f41499d20ea1a72a7ae2" + }, + { + "dataPath": "params_shard_357.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.78.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8e2d92f8f5eab5b23a5ec4598a67817d" + }, + { + "dataPath": "params_shard_358.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.78.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c5ad691c9ef5c233f0591ccd46ef1e06" + }, + { + "dataPath": "params_shard_359.bin", + "format": "raw-shard", + "nbytes": 12075008, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.77.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.77.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.77.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.78.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.78.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + } + ], + "md5sum": "3a2171ee6d2fea47e190c9ec3e8d99f3" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..d95aebac7d4b5d97e4052bb7cbe5bc87400fa455 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed387cf45a835bf9e9de38d9665d743cfc926ced7533a890a4959a246533691 +size 525336576 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..66a4fc96152e36f7d2222d0ca14e9652c3069c65 --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93738653fa1870b4a8ec4c539cd19d9e02d8a1730e599d5ad032ffaa6550658 +size 117440512 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..611c57ab70886444f49b738294c496503e5f73c3 --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99380595dd723d95a46af4762f6b160aa34b56be4fa2b3b110cccc9d7f3e9a51 +size 234881024 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e44e4dd5a51e977752d0199967f51b38c3778c2 --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f510c87c273c261d15c97d4875211008f069f9613468cb0f77869af4009703d +size 41943040 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..d79261c6aca91e4c58cecb53472331409d99c547 --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445d766d1b16d741e4fd07c685ca881db7eb287099f11fbdbc465825ec2c90e6 +size 33554432 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..f03df96943d69c191123a2d022cc1ce1ca498064 --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdefcee0be4f7797cdb1f0e33b4e3aa4dc09f420ec58953669db84e2cdb09277 +size 41943040 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..befeebc4576898006dcc7ff2b83bc146c3b41940 --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eca914235133d2c729c06f7bb19513af91b514647f902aa90d6b41cb6b00314 +size 33554432 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..5450232085ddf85134645a7fb51cdaba4617b07f --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005e51689bb6649fe4dc6229c56865c3e7569da1cf916d304fb6fbe47d5a16be +size 117440512 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..e1479fda73db5f5d862407aedb336e7e4d63a88a --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519a448ed0cc57ff4ac2b0be924b76dd03161943a5f1bc2945cb33fd42db93f2 +size 234881024 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d4e3ba6d4a4b61e0b15c58eda934e0432d90936 --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f5a27e0c1996e460ff91d6761893af2705ecc324551e2b8cdff01f7dce6645 +size 117440512 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..88715c3e5ac72cc8a0c62d83d8a0884f6d0bc68d --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a757a669b5951326e8ee1af9fef21e1445acb75d5966864bb1773fc46eabe42a +size 234881024 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b16951fea0282311fd04b7ec1ef8db1d251e26b --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:192df3b112f3e179a5ee86e4aa9dd13c82dfdabfa50e186091803aa712f8b8aa +size 26804224 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ef53777c248b8eaa85c04839f9fcff892a09d58 --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0540b3d69a2fde04c628a6458b2385b6207bb4d1769467275757fc899f7b2e17 +size 41943040 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e4822706c300183aaf002b754df86fd12d16101 --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0fe5cd08e500a23d941dac1e89fb666bc066a46e66d65ba0ac700a198fb974 +size 29835264 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..b99a0640e23c6df03942c5a24f0711f76b9818b6 --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2be93f7def10c2fe1f49c269f31a3187a142d5e27c6d36f190e97e77911389 +size 33554432 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..1df8774ebec78d63b6e218b39e7b7710c2b80259 --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8df2c92728339e09976028448cc1b971462efaa56c177b6debe4bc07a70850b +size 117440512 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..ff489eb8ac17070dc23706e427be89cbfb52535d --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb97a9161257317cecdaae4487871b2708279e49a15d58d782a0ac2f3e81ec57 +size 234881024 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5c52bdeae5fe411e02375489453cd277ff1cb5d --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f94664dced4e6e3721d11ff2a184c23ac97e868ef10a61d8979757ac32e019f +size 41943040 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3c0162ba72798a4781fffb54038fbbce3861455 --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a50f5f686549ab500520ecd0867ead98558a174e10341ef260b472b83a9069bc +size 33554432 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..de900532fd77d317e5a21d34c8ad70c525f5de35 --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2da5b26d8333ce74a330abfffaa00c97c2d0280d3b5248c2b915fb97a8def04 +size 41943040 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..86ed1197c4538eb77f5b939a60bbc2c62725ac52 --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7c10266f11d11e2ea56e9c9d4cfbdd5ceabe70ca0808e40a07b5f22d313e664 +size 117440512 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..204138b33362efdbcbb3b35983550165cc7c2e86 --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e984d6c444444f7fcef77faab52b8cb68fc0bf862c35a664f7eb24fcbcb6a5b +size 234881024 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..e4968c71a51ed41e41920be812986c6fbc744ee0 --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65843e23923011e0aa173df8b9c68ffd49fdf6216f35c28a6c96cf1205c53733 +size 28114944 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..ebb552e34e99e9029340f95b4070dea03edb6e3c --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658c6d359b42b2c7bd080e67decf495fca5ddf804a3900685c4848d99a09a541 +size 33554432 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2a5200a1a4f3a3bf2f0b0268be9193cadd66c6a --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409efc16acfb10e503c5d87eb326cd78485f2bda05bd30496335fe3374b7ab10 +size 41943040 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7a9ce6369b596966505d2a5d7f27c8e41ab8b74 --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca915e73479f410a80bd6a3e277b83bb6de113d2526f2f63b9435a5ea45ca0c6 +size 117440512 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7ce7400a4f22df2c1039763d2500fea0aa89e18 --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e25c887a50cf48e52c73f00e9dd5a7bf8ef3af75d3b2ed1526255b2ebe8eafa +size 234881024 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..94eb890ae588e9f41f98f24ae88065bb68d1b339 --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace5c4b5f77e396751d8dfd23b0267635a022af77443841a4a63f6823c88f7f2 +size 41943040 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1249aada8180a59f1de380561338db7ac9cc1ec --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24fde654749ee07ca58186fe8105f03a85879d683499d756e1da1e64e32d6f8a +size 33554432 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d9a266a9598e74da82b8e29a2102aac3c712045 --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2f0fec5da19448760ebc00ca8c5afeaeab097f541976f2a4c0139507f1aee1 +size 117440512 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f91023fda4ba9f5712e7672b8232f90f9162532 --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d93344f4bb825ca37a26e7953e3995b6e9427d469f8fde1f4b5d08fcaefaff1 +size 234881024 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..407ec3a5603730995c218bbcc5e03c7dbeb112f8 --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1965f2ab50bf0e0cb017598fd02980edb7b097ae174e04bee8b34637714c35ab +size 41943040 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..86d0a98f2a752d4df4fbbb78831f34343e170a66 --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7311c0b9315f393d6a0d23f9261e00eef7ccc658eb53cc01b34195de287c3cc0 +size 32817152 diff --git a/params_shard_128.bin b/params_shard_128.bin new file mode 100644 index 0000000000000000000000000000000000000000..65ceaa9d7626afa39cf50eb787d25c3f0de38d01 --- /dev/null +++ b/params_shard_128.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd781286821265883037eea31c3465b50b34eb6c049ac974e64710615fca2e7 +size 33554432 diff --git a/params_shard_129.bin b/params_shard_129.bin new file mode 100644 index 0000000000000000000000000000000000000000..21bc1399a43e9654538c02c73e56eddb23fdcb96 --- /dev/null +++ b/params_shard_129.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d98bb1170dbec011d6eb668ba7cc1f15386e7998ecc9aa9d81328fab4803244 +size 117440512 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..644a8a751a1a434063d11aa56aa3e0275e02fcc8 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e174f0f647cf2f53ff234712e9c8afec23d6ac2123eead3c7fa9a871f3ca88a8 +size 33554432 diff --git a/params_shard_130.bin b/params_shard_130.bin new file mode 100644 index 0000000000000000000000000000000000000000..50bc46fb432e3cb24176400a2fb05f9cf8d89b61 --- /dev/null +++ b/params_shard_130.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f03a075966a4a2287aceb2199609a3b48f10c555363332c9a749e1a59394ce +size 234881024 diff --git a/params_shard_131.bin b/params_shard_131.bin new file mode 100644 index 0000000000000000000000000000000000000000..2166692c426655e762189c11afd1b915431f388b --- /dev/null +++ b/params_shard_131.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76b8d325b8e32e7e8858a67a3ce5f70c25f9f1dd3bb612a12eb1e256df419b39 +size 41943040 diff --git a/params_shard_132.bin b/params_shard_132.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ae5a65170997e7e582ed6fca65f72e96f81fece --- /dev/null +++ b/params_shard_132.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69756b723f238bdfce0534e838d708c68202566fef3072d9e5dfaf0997d3b14 +size 33554432 diff --git a/params_shard_133.bin b/params_shard_133.bin new file mode 100644 index 0000000000000000000000000000000000000000..98b485877972c4a57aee71d91fd6a8f28b82e3d6 --- /dev/null +++ b/params_shard_133.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cfabb0b66248487292afb037a798f9a2a576d93f03d47fbc2a95b8a0116d9c9 +size 117440512 diff --git a/params_shard_134.bin b/params_shard_134.bin new file mode 100644 index 0000000000000000000000000000000000000000..799ee1a7cfbf47146c1e3a5129a83341b9da8c5c --- /dev/null +++ b/params_shard_134.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb0187c4a2edc9be9f1dc3ccf2191f323a1d93a27b2926cbaa4b7839fe2d386 +size 234881024 diff --git a/params_shard_135.bin b/params_shard_135.bin new file mode 100644 index 0000000000000000000000000000000000000000..487858e5f603cd73bdbb7be45fb0458f9e99db7c --- /dev/null +++ b/params_shard_135.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e65ab3947d26eee05160c4c98b593d781b28c44ab83a13970655efdbee105bc +size 41943040 diff --git a/params_shard_136.bin b/params_shard_136.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a9882d7e9d1bd6a55c3be87f30002bfe9fba7c5 --- /dev/null +++ b/params_shard_136.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:770d8efb6604760363c182290b7ea0e605039da273cd4a209db8a06e6ffd27ca +size 33554432 diff --git a/params_shard_137.bin b/params_shard_137.bin new file mode 100644 index 0000000000000000000000000000000000000000..df5b51687fd20df011c2f986e1fe8c1bba8e9425 --- /dev/null +++ b/params_shard_137.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:434a6e873350a1d46a072605f05a5e744f4e0e0a8e565fb981cc2501b0361654 +size 234881024 diff --git a/params_shard_138.bin b/params_shard_138.bin new file mode 100644 index 0000000000000000000000000000000000000000..23a6c73aa9f5306713c725a9a5bac3d8fb528890 --- /dev/null +++ b/params_shard_138.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473a65325c89244d7d71c9190cb5aaa5bf684ccc455d9a0b82f82edad40ddab8 +size 29196288 diff --git a/params_shard_139.bin b/params_shard_139.bin new file mode 100644 index 0000000000000000000000000000000000000000..bfd0dca1b315bfac3310ec7e07c295c372869102 --- /dev/null +++ b/params_shard_139.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a1688c5858b3b4ecfbc54e766c8561337141bc78d59dab190a4302685edcf9 +size 41943040 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..f3ec90e3f4a5d83f4e2f217ac5b6c632e4af2595 --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fdb26c5e56d3877bfa535bbb34e27b1ce60630f3d6485dffa9bd36d59edfe18 +size 234881024 diff --git a/params_shard_140.bin b/params_shard_140.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ede1571beb17342a548d82de4a6c6ae31b7b1bb --- /dev/null +++ b/params_shard_140.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9189bb0d153d809d1bc2dd4b848b4ffa345f1db8ff21944511d73ba1feef2c9 +size 33554432 diff --git a/params_shard_141.bin b/params_shard_141.bin new file mode 100644 index 0000000000000000000000000000000000000000..304be616ccc8d580060d0c7ba1d3c3d8a8fc9945 --- /dev/null +++ b/params_shard_141.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1063eaece6d69c2a579d4a2de787b0632e3727243ca20369b83852c376447215 +size 117440512 diff --git a/params_shard_142.bin b/params_shard_142.bin new file mode 100644 index 0000000000000000000000000000000000000000..a86599ceca85c4f108500f0e81fc68c31fc8d858 --- /dev/null +++ b/params_shard_142.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e1288c810d2eafbd3725b636654dac70d8fa542dbffe75bde776fe7e540902 +size 117440512 diff --git a/params_shard_143.bin b/params_shard_143.bin new file mode 100644 index 0000000000000000000000000000000000000000..55b14c258ef5eefede9d5d97c6892ccd4b5a0e68 --- /dev/null +++ b/params_shard_143.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b5595d12e8e1f843139c9005860a51e60df641d1b078f7fe172bbd98fa427a +size 234881024 diff --git a/params_shard_144.bin b/params_shard_144.bin new file mode 100644 index 0000000000000000000000000000000000000000..72da067b97fcf64674a290bb5f37b10d287be7d5 --- /dev/null +++ b/params_shard_144.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0791a4ad4312d6f233c25ff0a7d67a0f60340f54d52e66b0d988e1e2747184fe +size 41943040 diff --git a/params_shard_145.bin b/params_shard_145.bin new file mode 100644 index 0000000000000000000000000000000000000000..9eb04ad2f707ce45d278bd6c49ab2cc7d3f3583e --- /dev/null +++ b/params_shard_145.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175a6b156890ce23c18e3a1c6868614ce82140bede96088f1c39a4b2709d0e1b +size 33554432 diff --git a/params_shard_146.bin b/params_shard_146.bin new file mode 100644 index 0000000000000000000000000000000000000000..9459bbe09360343f98b78bf7743324114786e27e --- /dev/null +++ b/params_shard_146.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92dc9e5aab7febd45fd8aa88fa2b64bb0a8a69d46cc3458303034d872d53c083 +size 117440512 diff --git a/params_shard_147.bin b/params_shard_147.bin new file mode 100644 index 0000000000000000000000000000000000000000..daeaed10e63c41e41e3248fe5aab1171b5d373f2 --- /dev/null +++ b/params_shard_147.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec36a44842682575a05d92bf2cc0a1ce0f714dcab15e2334e2518fa89264b7d +size 234881024 diff --git a/params_shard_148.bin b/params_shard_148.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f5eda75242afc8e86e35a112f236c0f22ff9efb --- /dev/null +++ b/params_shard_148.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834c9e27bd696f95eafa0979d86b5915a61e068db714e8f3a1fbbbc1cd25a5f1 +size 30490624 diff --git a/params_shard_149.bin b/params_shard_149.bin new file mode 100644 index 0000000000000000000000000000000000000000..b855f1b401e812af1a42657967d764bb4401f8e8 --- /dev/null +++ b/params_shard_149.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c31c6eb2349fe897866c712d21788a4ed268501ccd199c6891105986d0668609 +size 41943040 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..50f98ab587d7ae2b8e5b73fbef1f0a05c88a51eb --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b616c4fa6018e748d8ea7288a8e29065f516f04b915768a3ea14574ad2ffde4a +size 41943040 diff --git a/params_shard_150.bin b/params_shard_150.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d4a4318a32d642c03753a98dec5d78304ba66a2 --- /dev/null +++ b/params_shard_150.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abf855bf6f650b8d2eae103bb6dd83b5da019443c9a358cf8fa15c5848853f85 +size 33554432 diff --git a/params_shard_151.bin b/params_shard_151.bin new file mode 100644 index 0000000000000000000000000000000000000000..152facc7cff56584d7c8672b96819516421e71d4 --- /dev/null +++ b/params_shard_151.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0261b3611b5c537225717d9a1634f62d5e5fa3928fa57b66543ae7b2db21d4c3 +size 41943040 diff --git a/params_shard_152.bin b/params_shard_152.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c11915ca7727b3a6ce0395b25a7e67f30672f80 --- /dev/null +++ b/params_shard_152.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf19aa046f40ca13ca57f36c3d9f5ac3422196749193e620eacf5e1d32b045b0 +size 33554432 diff --git a/params_shard_153.bin b/params_shard_153.bin new file mode 100644 index 0000000000000000000000000000000000000000..0dd67ebe2c257dd5c3de6959dfa4401e1958afff --- /dev/null +++ b/params_shard_153.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04253696597aaccb6893c91a1b5bcc5eaec9e03e32530d9f52beba28c197339 +size 117440512 diff --git a/params_shard_154.bin b/params_shard_154.bin new file mode 100644 index 0000000000000000000000000000000000000000..d400ee72d683969ba5a37dd8ce4e9a56bf4e9d50 --- /dev/null +++ b/params_shard_154.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80801de523dacf868c8362748fed62c94ae01d472740dbeac15e09e08ac1702 +size 234881024 diff --git a/params_shard_155.bin b/params_shard_155.bin new file mode 100644 index 0000000000000000000000000000000000000000..972bb3cc3557a45e1aad0d964351e8f558e0f25c --- /dev/null +++ b/params_shard_155.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5290982cf26176aa326769c3dd98ff7f846a43ddb4e1d75fe3b0716c090d2b08 +size 117440512 diff --git a/params_shard_156.bin b/params_shard_156.bin new file mode 100644 index 0000000000000000000000000000000000000000..cfbc62de7fbb7f95c6948bd927865e58300297da --- /dev/null +++ b/params_shard_156.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6682a14499a8520a123f6cbabe6e14379a4d9ccb19d250d30122fd5fa94c85ae +size 234881024 diff --git a/params_shard_157.bin b/params_shard_157.bin new file mode 100644 index 0000000000000000000000000000000000000000..96236a627bb561d84a688e21659bc2c89d7bb3f6 --- /dev/null +++ b/params_shard_157.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe5b123183aed53a31c75ba4999e63c81914dcdf332e7c667925710c849a4ad +size 26804224 diff --git a/params_shard_158.bin b/params_shard_158.bin new file mode 100644 index 0000000000000000000000000000000000000000..1593815be58e1bba105d2988a4fc34d58912c01b --- /dev/null +++ b/params_shard_158.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe703c05ab39e7ed8ae06c6566646bff4ff2cc57e21910a08f31aec544c3f4d2 +size 41943040 diff --git a/params_shard_159.bin b/params_shard_159.bin new file mode 100644 index 0000000000000000000000000000000000000000..3855765a3d9042dce04616ad81e75585c160da6d --- /dev/null +++ b/params_shard_159.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6317bac37e3ed1e7a47d9217b6577f3e0e6e47be1577dd9a737cf95c3dfe66 +size 33554432 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f7b70f6971dfb94993eb5eb66b34e2781f5caed --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bdeed6dc0e86941d94041a652148f33d7de3b4d939885565e6d013d01e7a845 +size 33554432 diff --git a/params_shard_160.bin b/params_shard_160.bin new file mode 100644 index 0000000000000000000000000000000000000000..6497fb41d772f9ce2a4b51d19a58cc3bfca7d5d8 --- /dev/null +++ b/params_shard_160.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc735bbdf43bcba2dca53e097009dac615ec65d38537ea9f896ae5c033a1f39 +size 117440512 diff --git a/params_shard_161.bin b/params_shard_161.bin new file mode 100644 index 0000000000000000000000000000000000000000..06a6859e30780f3712c871808f823672309fcd61 --- /dev/null +++ b/params_shard_161.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91acf4fe72da25bbe95a1729aa8d04478088b53f65d181e169135609a8bc2a73 +size 234881024 diff --git a/params_shard_162.bin b/params_shard_162.bin new file mode 100644 index 0000000000000000000000000000000000000000..80bd12d7313d111a2c274d6c6780b42e5c6b0f9b --- /dev/null +++ b/params_shard_162.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90da492290318872002d0037747dbd1a2e17393a1c8cc0beb49ef4f3e1ef9e8 +size 41943040 diff --git a/params_shard_163.bin b/params_shard_163.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d6f32b9035b50f91019d2a39745723bab2a374c --- /dev/null +++ b/params_shard_163.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a0ef7660af00a5620fef9b8706f3e70e549084149da776f5fcf162dbc5e0b15 +size 33554432 diff --git a/params_shard_164.bin b/params_shard_164.bin new file mode 100644 index 0000000000000000000000000000000000000000..6de8effea6003607bde6afba45c7ba44f60e950f --- /dev/null +++ b/params_shard_164.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f726e6d1622f0b8621049e60d26c87d92233acb5abe6f4eddad25d3c7a27b135 +size 41943040 diff --git a/params_shard_165.bin b/params_shard_165.bin new file mode 100644 index 0000000000000000000000000000000000000000..8626c4e76cb12281cfa77aa37d8270853a5e4ef0 --- /dev/null +++ b/params_shard_165.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87357a4af29d672029b6e392f67c251ba1585ae6c58261649a4e240a94ab095c +size 117440512 diff --git a/params_shard_166.bin b/params_shard_166.bin new file mode 100644 index 0000000000000000000000000000000000000000..c964030810a64129905b05b522eda85c05c49957 --- /dev/null +++ b/params_shard_166.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:398637362c98ccf6769dcf7c9b0cfd848327b47a0cce91756ba3a49aebf9bed1 +size 234881024 diff --git a/params_shard_167.bin b/params_shard_167.bin new file mode 100644 index 0000000000000000000000000000000000000000..6d0c7261a5a196b2111d38066b711dd943e34d40 --- /dev/null +++ b/params_shard_167.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29eaf4687dc84c41e0b7b39ee94bcc51840817f1779de7eadb4c04a153ea2756 +size 28114944 diff --git a/params_shard_168.bin b/params_shard_168.bin new file mode 100644 index 0000000000000000000000000000000000000000..14945f98555903cbe6d0acbf501ee6c7833fc97c --- /dev/null +++ b/params_shard_168.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce80fd6a4d4ac70ceee21b165de6020e2c9e013913cf3223f1585b7581cecdb3 +size 117440512 diff --git a/params_shard_169.bin b/params_shard_169.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd5556c54e5077eed68ce1c5182ae27a701a711f --- /dev/null +++ b/params_shard_169.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14c84956051402579673a4a7880c6afe229da087ce557b46bfad1ebb3944db53 +size 234881024 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..325e27e2ce48ebaec80a6414b8a554f73be161ba --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8721c3364c1bc36cd4b051e88f0d7b7ce5284a1deb35321497af8fa75aab6b0d +size 117440512 diff --git a/params_shard_170.bin b/params_shard_170.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c0f79c71fa5238b0aa21719202fe6f56c85f16c --- /dev/null +++ b/params_shard_170.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:906379ebfa757eaae6b0d73d4103d79346cf8f186d6f638b353de15afb0631ed +size 41943040 diff --git a/params_shard_171.bin b/params_shard_171.bin new file mode 100644 index 0000000000000000000000000000000000000000..84b61e7762d14f2abd34c75446e48f12f6af8941 --- /dev/null +++ b/params_shard_171.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea31c71b530abcf61a1e9bfd6d2c36da6ad778886d599ed8a4fd5a1fe50e326 +size 33554432 diff --git a/params_shard_172.bin b/params_shard_172.bin new file mode 100644 index 0000000000000000000000000000000000000000..46685d9cfbc6a79b635533d14ea985ad34aedf44 --- /dev/null +++ b/params_shard_172.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633a555f1340757f25e3b8ad94310a1603608295e6343e70094e546ae31788fa +size 117440512 diff --git a/params_shard_173.bin b/params_shard_173.bin new file mode 100644 index 0000000000000000000000000000000000000000..91986d4bac99f5c40ff1f1d3cc6938608d80abca --- /dev/null +++ b/params_shard_173.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840bd30c24c1bf15d0a237709b83ef9524bd265f0cb0287bb0d92edb11e004a8 +size 234881024 diff --git a/params_shard_174.bin b/params_shard_174.bin new file mode 100644 index 0000000000000000000000000000000000000000..e3b7dbe73d655a2258af687ead8407ff6339c103 --- /dev/null +++ b/params_shard_174.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b57aa3dd168eaddff68f7450cdf3cc9b2323a4296e63620e9557056d9ce19e +size 41943040 diff --git a/params_shard_175.bin b/params_shard_175.bin new file mode 100644 index 0000000000000000000000000000000000000000..6341b15b230b2a3bb8dff43084065bb592b8130d --- /dev/null +++ b/params_shard_175.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef3d7845cc33d22034c79dd600b9cd1f539d1f3ddef58aa0748a7067b772368 +size 33554432 diff --git a/params_shard_176.bin b/params_shard_176.bin new file mode 100644 index 0000000000000000000000000000000000000000..e501ee1183e5b301beb45316eab144fbd1929042 --- /dev/null +++ b/params_shard_176.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3153d507a6faf92dfebee2fe311599d12ba3b628cf111adb04d5c8eb06161ee4 +size 33112064 diff --git a/params_shard_177.bin b/params_shard_177.bin new file mode 100644 index 0000000000000000000000000000000000000000..77b817e27dd9b93b34c5f27733ed636da9077ccb --- /dev/null +++ b/params_shard_177.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b5f6b73012b10c9c5f5243eadd6718a87ee45d9f17b72fd52b89b17cbf1637 +size 41943040 diff --git a/params_shard_178.bin b/params_shard_178.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4c414b832eee914996b3be707f6387d89ee7ef7 --- /dev/null +++ b/params_shard_178.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09a0c43b397dbda6b3013a4c23c329b01dd090cc281395a27fb1c6ab0a22824 +size 117440512 diff --git a/params_shard_179.bin b/params_shard_179.bin new file mode 100644 index 0000000000000000000000000000000000000000..8930f9d2afffdf703fcf86e421a32dbc53cc5e33 --- /dev/null +++ b/params_shard_179.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c06853c727927fdad7ccf84b79aeecce53fd17823e3507b00915a0dca8caf812 +size 234881024 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..d4b1fc06ef5552921faa5714ed720ee37550dd1f --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0b9aeabd560747195726784b3b85afbb2fb56e6f4e1390d876a683c16b1676 +size 117440512 diff --git a/params_shard_180.bin b/params_shard_180.bin new file mode 100644 index 0000000000000000000000000000000000000000..aded0cf7ed626795352a0422c9baa5b6fb6e10b3 --- /dev/null +++ b/params_shard_180.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbaacd63d14761e3903d5dbd5d4d7a4a4071810534cbb8b04605fb8410796f19 +size 33554432 diff --git a/params_shard_181.bin b/params_shard_181.bin new file mode 100644 index 0000000000000000000000000000000000000000..86e7d8f84bbd727204dc6edd4f39a2d0e111ed26 --- /dev/null +++ b/params_shard_181.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1248d060ea5dd92388376a8843652ee0af9cfd43db6df8bf2272ed18f0ce8998 +size 117440512 diff --git a/params_shard_182.bin b/params_shard_182.bin new file mode 100644 index 0000000000000000000000000000000000000000..dacd60aed6bb1c2e1e8c7893608dd58a2dc3536a --- /dev/null +++ b/params_shard_182.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ed147614aeb21c4df73f8523d493a159585f4facbfc936e69147ee238234d1 +size 234881024 diff --git a/params_shard_183.bin b/params_shard_183.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c1bada8f518c4fb975a7cfcd9c409fc7d18f146 --- /dev/null +++ b/params_shard_183.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17f4d7dde1af76ca18719b472c1f9c1cbb3e51b2615cf726296f51cfc9891de4 +size 41943040 diff --git a/params_shard_184.bin b/params_shard_184.bin new file mode 100644 index 0000000000000000000000000000000000000000..b72e6e89470371074960018b5fa3e1e007d6f17c --- /dev/null +++ b/params_shard_184.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f464e6524577a4e81b7044529ea4cefb74d517011405a83079e0266cbc978dae +size 33554432 diff --git a/params_shard_185.bin b/params_shard_185.bin new file mode 100644 index 0000000000000000000000000000000000000000..050c9af9bf10bcb81e8ab46432a0874473f0f87f --- /dev/null +++ b/params_shard_185.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:042bb68cf4ab00e61e2be546f2a3b02a470ff9ccb74a7d438d27b12d1fedf72b +size 117440512 diff --git a/params_shard_186.bin b/params_shard_186.bin new file mode 100644 index 0000000000000000000000000000000000000000..58ab7d4b8e7e6050b5cd55080efed46d308bfc31 --- /dev/null +++ b/params_shard_186.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5100286c625c6c2ebb3a5fdbd43fd6f108258025b1cc42eeb2a106f238c09779 +size 234881024 diff --git a/params_shard_187.bin b/params_shard_187.bin new file mode 100644 index 0000000000000000000000000000000000000000..c75be1f0741105f8959ddcb659759ed0dab58652 --- /dev/null +++ b/params_shard_187.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1e15f87f2114e597ae54047b4fac4003d289194d89c92338b14fb64f81b3cf +size 31522816 diff --git a/params_shard_188.bin b/params_shard_188.bin new file mode 100644 index 0000000000000000000000000000000000000000..eae0154ed3ce54fde2ad57245d7c212b812401c7 --- /dev/null +++ b/params_shard_188.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77f0ef1005729324c2c02b41ccf323e07db3880c109587966867cbb670c7962 +size 41943040 diff --git a/params_shard_189.bin b/params_shard_189.bin new file mode 100644 index 0000000000000000000000000000000000000000..383bfa94b005d282f87f76bc819c4a55461ea60c --- /dev/null +++ b/params_shard_189.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6328a30bef8dc481fc976bfbfad207f2d69b0d1f733da25b8debd411eac34208 +size 33554432 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..2401662313e4139a581efed8370310f744e185b1 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1969bf6cf0c5d951d558ae7586e23a3466a2b5c65c08128770a53872c743a867 +size 234881024 diff --git a/params_shard_190.bin b/params_shard_190.bin new file mode 100644 index 0000000000000000000000000000000000000000..0aca220e5b384a1ae4f958e8734d7e3b8ad95ae6 --- /dev/null +++ b/params_shard_190.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:015e553d7a48de20336ae0e6174e18662942cfc8e26acca04afa31ca6c746782 +size 117440512 diff --git a/params_shard_191.bin b/params_shard_191.bin new file mode 100644 index 0000000000000000000000000000000000000000..2166391838a2982abb25430a2a5de74dfd796394 --- /dev/null +++ b/params_shard_191.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df37bf619c51a62c09a17b33ac47a0f8c1e9b331328fef6facb8b58f1f9ce4bb +size 234881024 diff --git a/params_shard_192.bin b/params_shard_192.bin new file mode 100644 index 0000000000000000000000000000000000000000..b36fab0e22ee2ea5598c9b339714ddb15563aacb --- /dev/null +++ b/params_shard_192.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d722eae64c015afecff66b863aede63bca25eacdee66c2b0c43f09efa3eec81c +size 41943040 diff --git a/params_shard_193.bin b/params_shard_193.bin new file mode 100644 index 0000000000000000000000000000000000000000..f758f6ced0affac41666c7244c233fba48d60159 --- /dev/null +++ b/params_shard_193.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24b688ace5fe065c96b70234a013dfc8281539491cdd1571da8ae728e8855db +size 33554432 diff --git a/params_shard_194.bin b/params_shard_194.bin new file mode 100644 index 0000000000000000000000000000000000000000..a6c8b0b3a224d0d0fd299d06ce973179b106f77a --- /dev/null +++ b/params_shard_194.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6b5c1d0e2d0c9857f468ec7b193cbeaaa668954dd0f5dfa77eb0f1ccc4dc3e +size 117440512 diff --git a/params_shard_195.bin b/params_shard_195.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac4b04a2b4b1f59034e418275c11ca1faa7c3321 --- /dev/null +++ b/params_shard_195.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6d1d136c18fcdf5f63588767f8dedf3c2adc9f13192c68c88560d8d293b406 +size 234881024 diff --git a/params_shard_196.bin b/params_shard_196.bin new file mode 100644 index 0000000000000000000000000000000000000000..40fe21468d1ec709b73b9569aebc661f2b39f003 --- /dev/null +++ b/params_shard_196.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202cc3e43d6b65d5cb6b776c5c3467fd3daeecbb64ab48255dd2b35756292a72 +size 26820608 diff --git a/params_shard_197.bin b/params_shard_197.bin new file mode 100644 index 0000000000000000000000000000000000000000..8883e3fb03155cc93289d333e1b4db16ad58db7d --- /dev/null +++ b/params_shard_197.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d7b1941ff3d672f96a61c0c8cf422a8002d9fae9351d707ea6aaa570a50cbb +size 41943040 diff --git a/params_shard_198.bin b/params_shard_198.bin new file mode 100644 index 0000000000000000000000000000000000000000..6846fd7063d1ab6c1c212a7384066d2fe1adce64 --- /dev/null +++ b/params_shard_198.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f17d1cf0dcc8f56b05c55d9b7e32a3be8e1aaa8918afcc28f522c8b17563da +size 33554432 diff --git a/params_shard_199.bin b/params_shard_199.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d6f8ba7580a411c95b007261352dd5f01116db9 --- /dev/null +++ b/params_shard_199.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:713f220601e14886c165d3c028f47012c452522625dae3c0240fecb854c9cae5 +size 234881024 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..49c2691023dba41938709cdf56ff96e8f14d5a0c --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8218b39da0558aa70276e1d6f05185afcf61acd073908df8b58bf20b558a905e +size 234881024 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..c22469d2edfb42ce76902976c3c1dd62aeaa95b8 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e526d588152035d9bd20186fe2e2216a349841a1e5aa0d587f274564c465cb6 +size 26804224 diff --git a/params_shard_200.bin b/params_shard_200.bin new file mode 100644 index 0000000000000000000000000000000000000000..632fdc1125761533bb9841e26c2d60de6b8ba68b --- /dev/null +++ b/params_shard_200.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bcb68a000baf45c3ee9753ba0ea7ce3d1f6f8ac7c942a04f8790d782744add1 +size 41943040 diff --git a/params_shard_201.bin b/params_shard_201.bin new file mode 100644 index 0000000000000000000000000000000000000000..f7b649d732591b026450309e22ec3ce04e6b944e --- /dev/null +++ b/params_shard_201.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec69b7681ce38aa05b6ff32c6e0a512cf9f24cb3220a18767431313e82eacf6f +size 33554432 diff --git a/params_shard_202.bin b/params_shard_202.bin new file mode 100644 index 0000000000000000000000000000000000000000..c065037eb90f960ff1e347108b934832b0fb0983 --- /dev/null +++ b/params_shard_202.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7743481c4041dd1626eee2d1e25f9c6a0ebfa22a35ba768c3d15a8dc997f244d +size 117440512 diff --git a/params_shard_203.bin b/params_shard_203.bin new file mode 100644 index 0000000000000000000000000000000000000000..2289b8428de199ee4ac576d313c2d3fbf643bb35 --- /dev/null +++ b/params_shard_203.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd5cda794d2db733836513efcece8eece9d934ecd78936bdc20da271863ad6c +size 117440512 diff --git a/params_shard_204.bin b/params_shard_204.bin new file mode 100644 index 0000000000000000000000000000000000000000..11a82c8cc5b9e67b6ca6d34e56135387109279d4 --- /dev/null +++ b/params_shard_204.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae839292a342eab75f3ee4af0121651fa136fb316a6ac541649583e41c55840 +size 234881024 diff --git a/params_shard_205.bin b/params_shard_205.bin new file mode 100644 index 0000000000000000000000000000000000000000..6bf15f37c9d96e545ad1d1da88522204f96360a8 --- /dev/null +++ b/params_shard_205.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a301981a9e326a8da99a4ef928bb378f3b0498783f0ebeeb9c14d8ab837191b +size 26804224 diff --git a/params_shard_206.bin b/params_shard_206.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d10b8d6ff654b0d62b4b6b97d69697e050903cc --- /dev/null +++ b/params_shard_206.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7676f85bc117445667ffe678e43ba79a318f17a02c21cce990996338cf38fb8 +size 41943040 diff --git a/params_shard_207.bin b/params_shard_207.bin new file mode 100644 index 0000000000000000000000000000000000000000..148830f74e6cf586b67cc05ef20b1db61c3d4c60 --- /dev/null +++ b/params_shard_207.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f697385625df4219a0fdc997002b5c4ea51bf9c23d23b23915505213a04bb91 +size 33554432 diff --git a/params_shard_208.bin b/params_shard_208.bin new file mode 100644 index 0000000000000000000000000000000000000000..959024db7e8e03cdfaa82ef88c335f67a607d0d4 --- /dev/null +++ b/params_shard_208.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5240845474310d09f9a9fa2cd6f574343b0510117fa1eb9c1364dc32aef6675 +size 117440512 diff --git a/params_shard_209.bin b/params_shard_209.bin new file mode 100644 index 0000000000000000000000000000000000000000..64081f104ec92b353c30c19adffba1fabbb19004 --- /dev/null +++ b/params_shard_209.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd216a8a79230c0275d870c4d443973bdbc1590d6b1d220bfdcbed2f6519d1c6 +size 234881024 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef4734cbd10d5c2e41f9be197ba9f49315cb68c6 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b40e42bad0c06c4115383bf6787e42bf4e1f9c48e589d86ac76a6fdbb4e2d5c7 +size 41943040 diff --git a/params_shard_210.bin b/params_shard_210.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ac6a45ecf0f5c6e5c36e22185d69467003fdcc6 --- /dev/null +++ b/params_shard_210.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b08e053b512ba0a351de93d48790e10ccc2ed6c670009db80e908cdd87add770 +size 41943040 diff --git a/params_shard_211.bin b/params_shard_211.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9e69811852e6756fdc3f77874d67c9a6cb4367d --- /dev/null +++ b/params_shard_211.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8db4ca4446fe847d31419be61def7c55396bd16b4bf95b8832f8334dedebb76 +size 33554432 diff --git a/params_shard_212.bin b/params_shard_212.bin new file mode 100644 index 0000000000000000000000000000000000000000..3aff76a484527cacf6ea3b20fee6f62222214879 --- /dev/null +++ b/params_shard_212.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1f8cc872adbcc9d730ae62e79f0fe2566f4ade7d5381c0516be38f10924c63 +size 41943040 diff --git a/params_shard_213.bin b/params_shard_213.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab6d42540d99ce754b8eb9acf4f1f92aefb7b9ec --- /dev/null +++ b/params_shard_213.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f54de067ece1ef34e8c3ebd7889e2eba4aace21c81884775286c059e2284140 +size 33554432 diff --git a/params_shard_214.bin b/params_shard_214.bin new file mode 100644 index 0000000000000000000000000000000000000000..d83c11cafc7e3c560bfe4cc21a6c1fe192e4302f --- /dev/null +++ b/params_shard_214.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da577c2e636f04b30ea6eef74c823791a5162465be7b811e1239327d4604551 +size 117440512 diff --git a/params_shard_215.bin b/params_shard_215.bin new file mode 100644 index 0000000000000000000000000000000000000000..2550bbbf7b608bf019808d324d4b2d3f4ff189cc --- /dev/null +++ b/params_shard_215.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0d355c4d1d7e45a34beb277b49648380432c80f3163dcdbb000e7aac024cf9c +size 234881024 diff --git a/params_shard_216.bin b/params_shard_216.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd21786ea421905d0b7e351d6018ca1897ce404b --- /dev/null +++ b/params_shard_216.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7eface7543c924eb6646e5c483046284660faf7ec37840a0f08977b877e6b3 +size 29163520 diff --git a/params_shard_217.bin b/params_shard_217.bin new file mode 100644 index 0000000000000000000000000000000000000000..23ac59bc26c9c25697168130f470e31b63073258 --- /dev/null +++ b/params_shard_217.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d03b271db4aef6e91bfbfea54b64d703f5846971624369806f6410bb339dde +size 117440512 diff --git a/params_shard_218.bin b/params_shard_218.bin new file mode 100644 index 0000000000000000000000000000000000000000..96b386a7f482220309eb381d4020ccbf6d48a2a2 --- /dev/null +++ b/params_shard_218.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9ea973a49424911c57d5eab5afac9c134f91874e095f453a259cfc9210a8f4 +size 234881024 diff --git a/params_shard_219.bin b/params_shard_219.bin new file mode 100644 index 0000000000000000000000000000000000000000..042c6e18b4fd88eabf76abc086354cf90146bd65 --- /dev/null +++ b/params_shard_219.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2b9d4d64c90b906d1853b2565ad7237f45d1a88fa1d90d53a0ea1b1a9c01507 +size 41943040 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..aa9f9ce737fff4088ffc7a8a8a9fd8a99ad9cec2 --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6e4ec796699adb77b052cdb8705be53df8d50b1465425b411137f7dd3e6c52 +size 33554432 diff --git a/params_shard_220.bin b/params_shard_220.bin new file mode 100644 index 0000000000000000000000000000000000000000..7db9797ffb784cf34dad378367c2634e0bad0b34 --- /dev/null +++ b/params_shard_220.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3cb63897651504830bfa77126c46030352e5be733edca3f94fbceec80c77cd +size 33554432 diff --git a/params_shard_221.bin b/params_shard_221.bin new file mode 100644 index 0000000000000000000000000000000000000000..7096ff816d0e638d9f5487c9bed789c73a7aef12 --- /dev/null +++ b/params_shard_221.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4896d588994ed0eba76eb3fc5edc9dba9cafd8784f583954ecf107945cae1bd9 +size 117440512 diff --git a/params_shard_222.bin b/params_shard_222.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f9b09e8f56906ad6425a07fb744c50243eecfdf --- /dev/null +++ b/params_shard_222.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4fdb873ead28e509e3a08c84123a1ab194362a67057ab51e963e82356e3f41 +size 234881024 diff --git a/params_shard_223.bin b/params_shard_223.bin new file mode 100644 index 0000000000000000000000000000000000000000..07d956dbb25d8ea7fa9ba78381524092ac525b8b --- /dev/null +++ b/params_shard_223.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:035ca53a00376450d26d24aa2a1f023f7b192da39eb6a4f24ce59caaeea86690 +size 41943040 diff --git a/params_shard_224.bin b/params_shard_224.bin new file mode 100644 index 0000000000000000000000000000000000000000..61783a4d226b21831d4325a40fa17ddb3560370d --- /dev/null +++ b/params_shard_224.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ca1ca63a713839c2f7e9f8a0c986c66d5a1f0018ebca7973ab5f6034ee80d2 +size 33554432 diff --git a/params_shard_225.bin b/params_shard_225.bin new file mode 100644 index 0000000000000000000000000000000000000000..8221c361f39a106b774dd00abc035cd0fa8b7d1c --- /dev/null +++ b/params_shard_225.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae90a27a73504c7f3f01f802b11734b4682f24fad37357fe13256257719b716a +size 33112064 diff --git a/params_shard_226.bin b/params_shard_226.bin new file mode 100644 index 0000000000000000000000000000000000000000..99f4c714257b6e747f1dc6bd8622dde1c4689c2a --- /dev/null +++ b/params_shard_226.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c9039d34c4e7bd92ed6fa11c6334adcc727112be25f2f9bdf6d78aab04230f +size 41943040 diff --git a/params_shard_227.bin b/params_shard_227.bin new file mode 100644 index 0000000000000000000000000000000000000000..b2d5a21104d085c632e46f15c822fa884d693df5 --- /dev/null +++ b/params_shard_227.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f436103cf0e80f946dad578e1a87a821ca0135528331b82f11f4572a1e9c139 +size 117440512 diff --git a/params_shard_228.bin b/params_shard_228.bin new file mode 100644 index 0000000000000000000000000000000000000000..432d87cf50510199f8b37714ee3d2c8ee6e63a7b --- /dev/null +++ b/params_shard_228.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8234cd4346986008ea1e4262a29919331d75c9f884595b9deea3d29d282f3238 +size 234881024 diff --git a/params_shard_229.bin b/params_shard_229.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e616e9c7a0b3086ae6700ade7d1980bcf285901 --- /dev/null +++ b/params_shard_229.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:338ffa44308e17d3c5e93d4f0abdba86df2d7e70f6a6a3ed1c5325bd5af009f6 +size 33554432 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..5dbdbac6adc67fab132f0de8391ff5cf1c90755b --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137da2e413f8324740961da6fd16d66daf35d25666a2a9ea3713ab9ed5bad728 +size 117440512 diff --git a/params_shard_230.bin b/params_shard_230.bin new file mode 100644 index 0000000000000000000000000000000000000000..693c5cb0bc886dcfe621b244dcfd8b91c43068b5 --- /dev/null +++ b/params_shard_230.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810020739989ce62112d9b8fba84fee7515ae63439ccea68add073c078c54e3e +size 117440512 diff --git a/params_shard_231.bin b/params_shard_231.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e5a025a5f3990edb03a65df47b409d5a28d30a9 --- /dev/null +++ b/params_shard_231.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bcdb3abaeb0918298072d597591688b9c28f22bb360e194afc5abfa16d26c43 +size 234881024 diff --git a/params_shard_232.bin b/params_shard_232.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b59818dc8bb3ff5f0e8112b2ec91f06fe790c16 --- /dev/null +++ b/params_shard_232.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738561885f4d0317fb96d313a649fa00464a8e8c4c866e5bf2132d1f7dcf7945 +size 41943040 diff --git a/params_shard_233.bin b/params_shard_233.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a6a51e0f4d05cc2d26f5d782b379d92815a1d50 --- /dev/null +++ b/params_shard_233.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8c73efb79a3e0ee829eed833db0445db017e7a87490e0508b442880e7cad249 +size 33554432 diff --git a/params_shard_234.bin b/params_shard_234.bin new file mode 100644 index 0000000000000000000000000000000000000000..5cbbecefe952e3faa66bd39a9685ca0b07889f63 --- /dev/null +++ b/params_shard_234.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad53f9041ed3816198434481c8880b608059c7b0d8b91f9479833fcd43b02100 +size 117440512 diff --git a/params_shard_235.bin b/params_shard_235.bin new file mode 100644 index 0000000000000000000000000000000000000000..240bd2a8d32fa9c54023d25c9c623fd32a97fd10 --- /dev/null +++ b/params_shard_235.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d40957f0e48c5d8257f5af43ca877d7fbd896de73dd7838b8ac3f6c5b887541c +size 234881024 diff --git a/params_shard_236.bin b/params_shard_236.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d42845772503a8bb0cc2f39bfde2c68d61d0237 --- /dev/null +++ b/params_shard_236.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd57e8e8079ede72fef871b9bee9820107ff5991035656e7dcd42745dcbbe1ae +size 31522816 diff --git a/params_shard_237.bin b/params_shard_237.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c2496d5269764e53fcdae4b46e0353358d423c7 --- /dev/null +++ b/params_shard_237.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8607a483f21cf5686851a3e79089e211b577408325e061ed62d367c4630d989d +size 41943040 diff --git a/params_shard_238.bin b/params_shard_238.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d5fe85d0314bbb47f383ef2269fdb3adf06b1d1 --- /dev/null +++ b/params_shard_238.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87cf93b14285911270bf82a213a870fab9648e6530bf2041796b223aaf57462 +size 33554432 diff --git a/params_shard_239.bin b/params_shard_239.bin new file mode 100644 index 0000000000000000000000000000000000000000..78ee88dc4a5cc9d7eb23149e861dbcdbfb24a8e1 --- /dev/null +++ b/params_shard_239.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3637833b124f0416245e4097610135ea89f42fc351d5c804e9f9478afed4c525 +size 117440512 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce2d1853ee72502fe773992fd20d42e08efd2a71 --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ee5aa9cdcea85bb264e550a388dd99da298172a51ba873546b4dbce6f657a3 +size 234881024 diff --git a/params_shard_240.bin b/params_shard_240.bin new file mode 100644 index 0000000000000000000000000000000000000000..6628c98ed7770b31eccb9cce9946e53b4b1c85b8 --- /dev/null +++ b/params_shard_240.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:300f768d4713e02c2f1041a94822cb67382a709557b437fed4997f7ad014b65e +size 234881024 diff --git a/params_shard_241.bin b/params_shard_241.bin new file mode 100644 index 0000000000000000000000000000000000000000..7b90684571c512b0a7772c88367da1bbbc93825c --- /dev/null +++ b/params_shard_241.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:546638b1cac49c00b1dd8b90a31928d7032ca36abee753f863b52d4d0a4e7ab8 +size 41943040 diff --git a/params_shard_242.bin b/params_shard_242.bin new file mode 100644 index 0000000000000000000000000000000000000000..27d8143bf2ca773277f26e9b802af2f0584daa10 --- /dev/null +++ b/params_shard_242.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b006350c5cc8d447a46460359e11ca2dc1f6838db905b2616e200c12e6a52b45 +size 33554432 diff --git a/params_shard_243.bin b/params_shard_243.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef21a501f051a658a1abc593251fbab75bffba34 --- /dev/null +++ b/params_shard_243.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac68a9648de1fcfafbbbc1daff7af07284d631c2c01969d1f0cdb8d618c94a4 +size 117440512 diff --git a/params_shard_244.bin b/params_shard_244.bin new file mode 100644 index 0000000000000000000000000000000000000000..7202f852e17ff92c5537666661bafa0e10d6d73b --- /dev/null +++ b/params_shard_244.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5fdc5542376c72af0732ce99e045748334ded59be3df39e557766e1795ea0e +size 234881024 diff --git a/params_shard_245.bin b/params_shard_245.bin new file mode 100644 index 0000000000000000000000000000000000000000..62923d02bc8f298f394c2c0e163db6f575f4f631 --- /dev/null +++ b/params_shard_245.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804d7f20cda62dc61973dec2e3d577844ee6f243121b039e1e084d0c6a349b83 +size 26820608 diff --git a/params_shard_246.bin b/params_shard_246.bin new file mode 100644 index 0000000000000000000000000000000000000000..6194ac3af495dbefc9f38e881adb28434ea50e69 --- /dev/null +++ b/params_shard_246.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9af929d74221764ad82c4571340569ca18a5c8a9c5695213d3f3c918606b7d +size 41943040 diff --git a/params_shard_247.bin b/params_shard_247.bin new file mode 100644 index 0000000000000000000000000000000000000000..817c3d1c3f370f66f8bfed6b1f96ba84e41ffeea --- /dev/null +++ b/params_shard_247.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465a8b6a08ad468dfec574c305ffe00d4ccc00f71a8f3b56639d938d0bfd032e +size 33554432 diff --git a/params_shard_248.bin b/params_shard_248.bin new file mode 100644 index 0000000000000000000000000000000000000000..876157489b6275c669fc56e402c164bb6468ab0b --- /dev/null +++ b/params_shard_248.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c49cdb80998db4d80ffce8d91e8b0b4a08124feea0c30643cd269355dd9e90 +size 234881024 diff --git a/params_shard_249.bin b/params_shard_249.bin new file mode 100644 index 0000000000000000000000000000000000000000..aadc8a69c162cd37ae21181462d1da0c749b234c --- /dev/null +++ b/params_shard_249.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4dd8d3c3b2d8440eecfc11eb829096d624fe34a0fd51907d7f07db405d7192 +size 41943040 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec88b82021c67bd755ac6919eed15df8fbd5211a --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37bbf3c988d9e037dd0c7428c3a14c533e1f4f4bf2290e1a0a75573e684ebc8e +size 41943040 diff --git a/params_shard_250.bin b/params_shard_250.bin new file mode 100644 index 0000000000000000000000000000000000000000..5ac5f371bb345534ec6b67867c2cbdffe802f766 --- /dev/null +++ b/params_shard_250.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dcddbbcc51e592fc62b61cc41c5f965140c3a154ec21c1e466b13bcb79bcced +size 33554432 diff --git a/params_shard_251.bin b/params_shard_251.bin new file mode 100644 index 0000000000000000000000000000000000000000..c1d14829550440791d35cbec0dd20de4928ef7b9 --- /dev/null +++ b/params_shard_251.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718555cb94032613eb836d80e19b5d72619fb542893581ada83ee89b3583ff6a +size 117440512 diff --git a/params_shard_252.bin b/params_shard_252.bin new file mode 100644 index 0000000000000000000000000000000000000000..317a70aa813ee650f7d0e757446b7a26d035b4f4 --- /dev/null +++ b/params_shard_252.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e68c096327488c33597ef846c17403987aa6b7da9d3bb334983dbf38c13ad978 +size 117440512 diff --git a/params_shard_253.bin b/params_shard_253.bin new file mode 100644 index 0000000000000000000000000000000000000000..5985d4778a75be6c5ff2b2a5c9cb1631c94968bc --- /dev/null +++ b/params_shard_253.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cefb35300f8fbdbd97df7a8d03e41fc9d1ddfc5a083d9dfcb5987532fdb76a8 +size 234881024 diff --git a/params_shard_254.bin b/params_shard_254.bin new file mode 100644 index 0000000000000000000000000000000000000000..11d96d489bc0d61c0821792751391a7e3c9787f7 --- /dev/null +++ b/params_shard_254.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343683214cf1d9b076dd6b9189acb7d204e32a6b1062059faf9a84ef83bb9dec +size 26804224 diff --git a/params_shard_255.bin b/params_shard_255.bin new file mode 100644 index 0000000000000000000000000000000000000000..c668508b50f954c7fd245791a592dd89ea7ec36c --- /dev/null +++ b/params_shard_255.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:652058e812d3feebd243c0062f2a4c85e4030694045e95aa292ea0064657e19e +size 41943040 diff --git a/params_shard_256.bin b/params_shard_256.bin new file mode 100644 index 0000000000000000000000000000000000000000..187cff4c98f3ddf6a068a43e562ddb3865412513 --- /dev/null +++ b/params_shard_256.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0bff2d940f435b203079b36daa6fbb8005bfe57b833f5404086d8216f3fa754 +size 33554432 diff --git a/params_shard_257.bin b/params_shard_257.bin new file mode 100644 index 0000000000000000000000000000000000000000..445aa21a5941b40e2a76a2b88548f80e2d7b855a --- /dev/null +++ b/params_shard_257.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ee978d77a9718370cafea71343d09e78d904be6614ff01fa8e53a439ce001d +size 117440512 diff --git a/params_shard_258.bin b/params_shard_258.bin new file mode 100644 index 0000000000000000000000000000000000000000..28eacee385526c4b8acbbf2b5272f418368d14aa --- /dev/null +++ b/params_shard_258.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4d70c06d0ccf30c5fd9998c7344bf04c1b588147ebd19db1683b699447cbf2 +size 234881024 diff --git a/params_shard_259.bin b/params_shard_259.bin new file mode 100644 index 0000000000000000000000000000000000000000..63093cc9591d1e6b1d1bb0f817fc7d819b57ae3b --- /dev/null +++ b/params_shard_259.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f93a534a1ff494fb5b6f4facd7da5c60b0ac47ad5d6dc9eb6ba739f7107fa0e +size 41943040 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..82a5d170f90d1266dcfc746d2313cb3ccd1887db --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d8ab44758ec621036deb6be9c94a7b5e930cd388aab7143163df1357a2fb4a8 +size 33554432 diff --git a/params_shard_260.bin b/params_shard_260.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd39c49cf5f2b3fca09bb94c2f60e29423a5d19f --- /dev/null +++ b/params_shard_260.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:046c8aaa5b661f3124ae44eefdb33efe05d6476b5991f0ea6408a22d3f80a963 +size 33554432 diff --git a/params_shard_261.bin b/params_shard_261.bin new file mode 100644 index 0000000000000000000000000000000000000000..33868b7bf0d09da358d7c9e7d988c51ea1831084 --- /dev/null +++ b/params_shard_261.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ad2cbacf3830f7123fc388375212f654e4dd413203539d0764cdccbee96bd9 +size 41943040 diff --git a/params_shard_262.bin b/params_shard_262.bin new file mode 100644 index 0000000000000000000000000000000000000000..2734550b2520fdb9e18ac3c3db46eeb6df3b321c --- /dev/null +++ b/params_shard_262.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5783ab510142979c5e76bbd1c56bdb90ce4249ab05937d56448ae6f4f7d1e93 +size 33554432 diff --git a/params_shard_263.bin b/params_shard_263.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d0047e9bfbf0267e89a7d17a3306280793a9ee1 --- /dev/null +++ b/params_shard_263.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:986917fc9faf94f7b9947d8b7e3c182f35935214a09f50e7474990e1ae033a29 +size 117440512 diff --git a/params_shard_264.bin b/params_shard_264.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ad6a5e164a8841595060c9fd2a7008360cc9ea0 --- /dev/null +++ b/params_shard_264.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19aebfa4a8ddec0a617771c24870ba47aa3b65a90e396c9bbb7c6f7d00dd80d0 +size 234881024 diff --git a/params_shard_265.bin b/params_shard_265.bin new file mode 100644 index 0000000000000000000000000000000000000000..a07273143043b5c17b2f188757cd88a7155896b8 --- /dev/null +++ b/params_shard_265.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c17659ac7d4715620d26754315cfbb1436389924e1db588906b1e89a0e14ac5 +size 29163520 diff --git a/params_shard_266.bin b/params_shard_266.bin new file mode 100644 index 0000000000000000000000000000000000000000..34ec612f34195b6758ccf82fc235435af8ba533d --- /dev/null +++ b/params_shard_266.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1490690a5c87d623d544e5d82ae4650b81d0c1373d49a7c8d71f8b68d254387 +size 117440512 diff --git a/params_shard_267.bin b/params_shard_267.bin new file mode 100644 index 0000000000000000000000000000000000000000..902d01396f24483a6228f03ceca2b0a8b0d51647 --- /dev/null +++ b/params_shard_267.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bd859499de7baaccaee8742836b7076e74b843f3dbfb75edf0d7bead56bcb12 +size 234881024 diff --git a/params_shard_268.bin b/params_shard_268.bin new file mode 100644 index 0000000000000000000000000000000000000000..8382ae1d9573b808acc40237b7ba9af8cdc7a26d --- /dev/null +++ b/params_shard_268.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9cd7e599fe1d0ed8cdcc0831f38be6d20680b3567ecf4555ef6a9df70f4cfd +size 41943040 diff --git a/params_shard_269.bin b/params_shard_269.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ce4e236b781eea3edfa9202f68ce93f9cd319ce --- /dev/null +++ b/params_shard_269.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a15c75345f9e91e373efab6ff344d2b4306d8f84e1d0cc239e790e46ef1187 +size 33554432 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..41b3a5a49812fb7b5a1138ecdfa5d35c2c713a60 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc05f80d9fb5bf3662b5cdc448d203d71a80b06bbcdf8046c786b223744adfc +size 41943040 diff --git a/params_shard_270.bin b/params_shard_270.bin new file mode 100644 index 0000000000000000000000000000000000000000..8593cb2527f996a4bfd92471ecf31087cc9d20b3 --- /dev/null +++ b/params_shard_270.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f87ab9fd4677bbcca07c4bcd37593d7a1195bb23bec988f37c5eb8ae8a113241 +size 117440512 diff --git a/params_shard_271.bin b/params_shard_271.bin new file mode 100644 index 0000000000000000000000000000000000000000..943b1bee970b9fdadfb5e46e087d0cbc6660e774 --- /dev/null +++ b/params_shard_271.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2987e934f285d6c64978df806f1a0c153d1aa26c2b0640680bfc148dba774eb0 +size 234881024 diff --git a/params_shard_272.bin b/params_shard_272.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab483ec7eebf4e2977f880c00dfd94127c95ce1c --- /dev/null +++ b/params_shard_272.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adb96a60eb644ff53fb19e3ed725d684b095e3209a86b767a1037a2400320e06 +size 41943040 diff --git a/params_shard_273.bin b/params_shard_273.bin new file mode 100644 index 0000000000000000000000000000000000000000..2509f41a9799e3a0a26cb3453310112bf8408b67 --- /dev/null +++ b/params_shard_273.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d27cdd9e4007b75d9fa045f661f131f9b4c51a6355316ca8b1e0eb1518996b +size 33554432 diff --git a/params_shard_274.bin b/params_shard_274.bin new file mode 100644 index 0000000000000000000000000000000000000000..c8132c01341342876636a09b53a5b04c99711ae2 --- /dev/null +++ b/params_shard_274.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09e74915052b465c2fe5a49257206f013fd2f00da1b5293506a78ae2b6b880c +size 33112064 diff --git a/params_shard_275.bin b/params_shard_275.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea4b178c2e4b132111fe8e22bb46aa4a50dd1664 --- /dev/null +++ b/params_shard_275.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e2f53d10de55cdf272003ad8da041b0c91edb95758e566a8de56e24d836332c +size 41943040 diff --git a/params_shard_276.bin b/params_shard_276.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e1ea5a4ea6ac18ba21fb8c9b7e94ade35150d2a --- /dev/null +++ b/params_shard_276.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6581a03efab5a6d44047bcaeddafa092f2f351fdf4eee2867cbf91fa7a21d993 +size 117440512 diff --git a/params_shard_277.bin b/params_shard_277.bin new file mode 100644 index 0000000000000000000000000000000000000000..5eb97274d77570f7a8143c82f41fbf2e53239827 --- /dev/null +++ b/params_shard_277.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de2722c07da549d7e7f8f83e98de4390d199a4bf8177f706f65587b2f684720b +size 234881024 diff --git a/params_shard_278.bin b/params_shard_278.bin new file mode 100644 index 0000000000000000000000000000000000000000..eed5090b1de6d87a002902574b1f50fd006a10a6 --- /dev/null +++ b/params_shard_278.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9a460ffb3bf924e0f4d74800a45190320c829aed9eeb08ae76ba716351b1cb +size 33554432 diff --git a/params_shard_279.bin b/params_shard_279.bin new file mode 100644 index 0000000000000000000000000000000000000000..298a50e60602e956c1b06db354caecca9718d410 --- /dev/null +++ b/params_shard_279.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7811a01599e2f6e2a702488874cf52d43a1bfa2ef05d1c226d3fbd2d3ffe811b +size 117440512 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..9162e66f983f51f3586b223335d84811ee2e6bc5 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f65b1c7633c18583c4bd47706fa48b39b67abbe792caf7615bbb93abd601e49c +size 33554432 diff --git a/params_shard_280.bin b/params_shard_280.bin new file mode 100644 index 0000000000000000000000000000000000000000..29c6f5d8721f5971ca34af3076d7692af6b5ce71 --- /dev/null +++ b/params_shard_280.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ef61286593b73f2be727042bff1e0243ce86469d16d9414c0fc36f271a0758 +size 234881024 diff --git a/params_shard_281.bin b/params_shard_281.bin new file mode 100644 index 0000000000000000000000000000000000000000..ddc83fd883f418369549edf7bc78495767672230 --- /dev/null +++ b/params_shard_281.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f6702686525aeb73e0fecefcf53a6f1c7db0d3752fb39eb71969b41353b25b +size 41943040 diff --git a/params_shard_282.bin b/params_shard_282.bin new file mode 100644 index 0000000000000000000000000000000000000000..d45d9cf30d73f061a7e5235cd40889e6a4fc947c --- /dev/null +++ b/params_shard_282.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4923151b98787b7c1581277c17d218723c17fbd40998a5ef3be8b3ac4ee15e +size 33554432 diff --git a/params_shard_283.bin b/params_shard_283.bin new file mode 100644 index 0000000000000000000000000000000000000000..522ed483fbcd0ec34275d7f81e3065ca308bb1ff --- /dev/null +++ b/params_shard_283.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d8f0a556f4bcbde50a6db1587479e0c634e17433e7b1a31fd7314676f739d5 +size 117440512 diff --git a/params_shard_284.bin b/params_shard_284.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0a04e5245e5c5d0438c7a8d05159a1e7f06483c --- /dev/null +++ b/params_shard_284.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71206440053864d98254a12d514091294247893c14079a47c424a4754507132f +size 234881024 diff --git a/params_shard_285.bin b/params_shard_285.bin new file mode 100644 index 0000000000000000000000000000000000000000..c6cacc195c811bb053a7570688d1dbe349e3aff8 --- /dev/null +++ b/params_shard_285.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fca0c5fe2285338aa3b49ab62d72ad2f894a0cbcb7425ad34c1b5ba2650d875 +size 31522816 diff --git a/params_shard_286.bin b/params_shard_286.bin new file mode 100644 index 0000000000000000000000000000000000000000..87b2781ad08575476a3a8b1faad890e879c1b1d4 --- /dev/null +++ b/params_shard_286.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9ae9143f580112fce0d83648b3b9b939dfb3e4ad21bc66e9e3db9a5532fb37 +size 41943040 diff --git a/params_shard_287.bin b/params_shard_287.bin new file mode 100644 index 0000000000000000000000000000000000000000..53166908bece272cbd8ea1a63a3fdf27d6e2c08b --- /dev/null +++ b/params_shard_287.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb27418b3ef6613951cf59300c2437e6afe76cfc034c68f35402c522ff4ece69 +size 33554432 diff --git a/params_shard_288.bin b/params_shard_288.bin new file mode 100644 index 0000000000000000000000000000000000000000..e56500997bdb86f47bdda1fc8b896aa515c419fb --- /dev/null +++ b/params_shard_288.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f21c940e0ca48433b374e7e34f2eb71881730a7556fe88dbe0fbbf4627275e +size 117440512 diff --git a/params_shard_289.bin b/params_shard_289.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac1701475108a396a071fd1b328e63c4a55c9103 --- /dev/null +++ b/params_shard_289.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703781fefa62bd750eda3f44f66221ae436ff034a92963fef49a90f596cdbc8b +size 234881024 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a876a5da22acb8e92700887f90e1dbc70dde4eb --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbc93031a81fd2e11c816539cc4bfcfcdc1879769d33d95f41f89b26e1b4d28 +size 117440512 diff --git a/params_shard_290.bin b/params_shard_290.bin new file mode 100644 index 0000000000000000000000000000000000000000..e1fcf4de5ddac2294a7eefeebc505ccaf36dc5b3 --- /dev/null +++ b/params_shard_290.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f08d56cfb98068d37bbea9089fcdeb52dbeacb0bb10dbe32e27b595d09b007 +size 41943040 diff --git a/params_shard_291.bin b/params_shard_291.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8583551ea4c69daf05221d85a1528de9f47c31b --- /dev/null +++ b/params_shard_291.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a989bd2ea272b9ebe1c2b662df86fa381bf64fe82a0b524c0218b94a98389e4 +size 33554432 diff --git a/params_shard_292.bin b/params_shard_292.bin new file mode 100644 index 0000000000000000000000000000000000000000..20f23670c47f1138d76d5ccfec52df87328bf668 --- /dev/null +++ b/params_shard_292.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d2065b9816b13179b7d253267a410bce652a481bcac09b36cf9b04a5bf5b87 +size 117440512 diff --git a/params_shard_293.bin b/params_shard_293.bin new file mode 100644 index 0000000000000000000000000000000000000000..27eb85ef032a07d7d0770294d28b191cbf62d453 --- /dev/null +++ b/params_shard_293.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466ce94f44cb8b27f314a82e5e586a31078a8691b0536c1228f5009e36c1aa50 +size 234881024 diff --git a/params_shard_294.bin b/params_shard_294.bin new file mode 100644 index 0000000000000000000000000000000000000000..f21b4f0c96acbdac4260875c81371a2b7698e842 --- /dev/null +++ b/params_shard_294.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a01667d7bb851cd99a7c8cfc1fc118e06a2324eacfd33e5ca84f3f9fbb44625 +size 26820608 diff --git a/params_shard_295.bin b/params_shard_295.bin new file mode 100644 index 0000000000000000000000000000000000000000..afba55da38d012c82a0f1be9516e3e9b0534ef71 --- /dev/null +++ b/params_shard_295.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a007657cc127a0454ed17f7ede2f3847959cb9a8505e7de82d120ef18132ca61 +size 41943040 diff --git a/params_shard_296.bin b/params_shard_296.bin new file mode 100644 index 0000000000000000000000000000000000000000..a9862e21b85029b36d8d4087510ab7347731ae1a --- /dev/null +++ b/params_shard_296.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c61b7e1aea7728528419a3d28e301153f102e6cd039f5d21fd240f1b7b98402 +size 33554432 diff --git a/params_shard_297.bin b/params_shard_297.bin new file mode 100644 index 0000000000000000000000000000000000000000..046d9f3f4ba89167f176704da16b40615cb470df --- /dev/null +++ b/params_shard_297.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5367752d1a7078b51464a907c29fd1401eaf030f1635cc16895844322a159a +size 234881024 diff --git a/params_shard_298.bin b/params_shard_298.bin new file mode 100644 index 0000000000000000000000000000000000000000..b81f881adfb113f484076d3c303cb3c3b4efbed1 --- /dev/null +++ b/params_shard_298.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c558969a78061b8ae135ce5a96cb08d36b9de18c2c892892647182ddf3c21c8 +size 41943040 diff --git a/params_shard_299.bin b/params_shard_299.bin new file mode 100644 index 0000000000000000000000000000000000000000..b96a4b538d7e5e2927c1297286af17368e04e3fb --- /dev/null +++ b/params_shard_299.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5350493bd9df87f311170c359b31dc032f2f18f90cbca31e8cd65db61a72e8e5 +size 33554432 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1ada8bb189a54300785e816aaee014dec03d228 --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d48fc4321d0626c73aca768025e0a8958c8070385d0dae49200e2cedb4e3ddb +size 117440512 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..b03b40f6e116b317fc2d3d089ffa0aecc9c09fa9 --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7842bfb64c1b231905677b1d7a8cd1d3490947e504b6a439343580a3edcbb7 +size 234881024 diff --git a/params_shard_300.bin b/params_shard_300.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a2eaca4a9a848a13a3fc7818c225cb460ee7813 --- /dev/null +++ b/params_shard_300.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a4df0c5a0e153bb656a082dffeb67e8035aa4e529aef5d817b0f8078718e7c +size 117440512 diff --git a/params_shard_301.bin b/params_shard_301.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ea0c5c9b16daf47e14fa073a218e69b77dbb033 --- /dev/null +++ b/params_shard_301.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da27c3c4cf50b0149cecb053a1c25f2baaa948903574b3fa870881756608579 +size 117440512 diff --git a/params_shard_302.bin b/params_shard_302.bin new file mode 100644 index 0000000000000000000000000000000000000000..4fecbd7f86f3dcf192bb032ea7640b53908e1cb6 --- /dev/null +++ b/params_shard_302.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf412b858cb41a25f3dc119103a1a7cb5e29cfc26c9bd396df8cafffbb0e9cd8 +size 234881024 diff --git a/params_shard_303.bin b/params_shard_303.bin new file mode 100644 index 0000000000000000000000000000000000000000..aa4552bf04c31fb2c6a1c092e784860d5ecc9291 --- /dev/null +++ b/params_shard_303.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3693f14e8c213385d0632e741d513f4a9061877d3fdec8cabd58b3a63f1c2f00 +size 26804224 diff --git a/params_shard_304.bin b/params_shard_304.bin new file mode 100644 index 0000000000000000000000000000000000000000..13c891fd97f5b3886bd225ed97afa31afb71b65e --- /dev/null +++ b/params_shard_304.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c308d0efe1ee801ba7cac2f3cd3abc905da8c37f1586383ca5ea7f4a411c0ff +size 41943040 diff --git a/params_shard_305.bin b/params_shard_305.bin new file mode 100644 index 0000000000000000000000000000000000000000..1155d5f2bec69c2ea27260aa568706a18e62bc95 --- /dev/null +++ b/params_shard_305.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b951f01065ec43ce8af98bb5a4feb6b9afd62202fb19bfa00889ede5bc28a6fc +size 33554432 diff --git a/params_shard_306.bin b/params_shard_306.bin new file mode 100644 index 0000000000000000000000000000000000000000..b529d39a763b7eb22912df044c8fbe91bdae70f6 --- /dev/null +++ b/params_shard_306.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b7a0d37608965ca1661e8a690fff5091c9775b181cb4c6988c4e563990269c8 +size 117440512 diff --git a/params_shard_307.bin b/params_shard_307.bin new file mode 100644 index 0000000000000000000000000000000000000000..f0fa8521f2773b6f9a3958a283f7580afa2e12ca --- /dev/null +++ b/params_shard_307.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f672c36b9cbb3d87f9e27ab4973d9a240a18a30928b0131bcb0a2a17b1dfc2 +size 234881024 diff --git a/params_shard_308.bin b/params_shard_308.bin new file mode 100644 index 0000000000000000000000000000000000000000..53ba9416513f45db8e00f8d4a068ac2783f585c5 --- /dev/null +++ b/params_shard_308.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5130b265b1862d3783f98e3441ce54db3647ef42520b5d130ca6d973d626fa23 +size 41943040 diff --git a/params_shard_309.bin b/params_shard_309.bin new file mode 100644 index 0000000000000000000000000000000000000000..3fe3d3de569aa37a1968fa376808da640dc6538c --- /dev/null +++ b/params_shard_309.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bee0833fcbd566fa56be58a9dd48d447da1a877647d4d6f5e96dcc134f1c771 +size 33554432 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa3f2870d1aad6bb45fbaebba2239365bbf787f0 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96989c6740bd774d1fffb9d98239f7dbae8ff82f280c523ac3da8cdc45c86ec +size 29163520 diff --git a/params_shard_310.bin b/params_shard_310.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e4b37c28d5c3d4be6eb6d750dfcc66129043966 --- /dev/null +++ b/params_shard_310.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5ea484b4deef572edbf1a50cc8f69f2d3f0b62525217b7c93619f6d95c5b56 +size 41943040 diff --git a/params_shard_311.bin b/params_shard_311.bin new file mode 100644 index 0000000000000000000000000000000000000000..8dc340196a0dd095c5d1d1638a78355c5c072847 --- /dev/null +++ b/params_shard_311.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91821368dba110c5c32ce8e760aae46466d54879b915018eb677842c1432ddc +size 33554432 diff --git a/params_shard_312.bin b/params_shard_312.bin new file mode 100644 index 0000000000000000000000000000000000000000..5157b60361b07fdda6e2d7d99ced0f10199d2c2a --- /dev/null +++ b/params_shard_312.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f7df66c6554b51cdee1c8cbc47dcf615f0474c3ce7aecfa8ead654a14445b10 +size 117440512 diff --git a/params_shard_313.bin b/params_shard_313.bin new file mode 100644 index 0000000000000000000000000000000000000000..c38d8d87b97110751f6c0dbe18f559e4e06bbc23 --- /dev/null +++ b/params_shard_313.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45987a0648ccdec882a25602fab951eb4a28f3b301adc41283d01a44bab89427 +size 234881024 diff --git a/params_shard_314.bin b/params_shard_314.bin new file mode 100644 index 0000000000000000000000000000000000000000..31e6218f0a19c438bbfcc42caee8328c71a1e96b --- /dev/null +++ b/params_shard_314.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f68d9f359b0bdeee3a9776a3c8bd553c493009a95306ad2d880fe227166cc11 +size 29163520 diff --git a/params_shard_315.bin b/params_shard_315.bin new file mode 100644 index 0000000000000000000000000000000000000000..6c69aab863045b3e1067c7e3458694ce87072ee7 --- /dev/null +++ b/params_shard_315.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb66ca96106edaa0b149a42147bdfbc3bc1bb1720549e1de1cf7893a8384d18b +size 33554432 diff --git a/params_shard_316.bin b/params_shard_316.bin new file mode 100644 index 0000000000000000000000000000000000000000..87f3543fc971db00c7a44c79bbca2cd3bce7666b --- /dev/null +++ b/params_shard_316.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623dc2d0adacb4e470307a4fad6908d1eb0dc01e260e3b6b489d2186bf34b4ee +size 117440512 diff --git a/params_shard_317.bin b/params_shard_317.bin new file mode 100644 index 0000000000000000000000000000000000000000..1226cf39f981e641c31cbc1999dac160cd6964bd --- /dev/null +++ b/params_shard_317.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f056e4547439f8dc08bc8935b9d0f3fb147cebcd4d06386faf15c051717d4e1c +size 234881024 diff --git a/params_shard_318.bin b/params_shard_318.bin new file mode 100644 index 0000000000000000000000000000000000000000..652c6ef616b7c2b5136cc105e40f094940a4795b --- /dev/null +++ b/params_shard_318.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf53592c31c86b291261db824ad935c92755050257578429d94433d98f6192f0 +size 41943040 diff --git a/params_shard_319.bin b/params_shard_319.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a6b64a28251f0c564c4c7a93271aaac528380b5 --- /dev/null +++ b/params_shard_319.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f189a8e16ee2d678b4cf4029210124139320263ac403d71b040ea132c6522976 +size 33554432 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..34ee1decb2a9ded21956e478edf550866835aa70 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527c74147aa7d458b13cd269fd7a856144f0ae690d4bb71ccf45ae93183db1d2 +size 41943040 diff --git a/params_shard_320.bin b/params_shard_320.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ed85f6569f5d240f0ce5e85c55825ce8bc60d2c --- /dev/null +++ b/params_shard_320.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e15337ad6fc39ad606e7a54dd7c74c7b2952766c1c75865c9fe2274e7d0e73 +size 117440512 diff --git a/params_shard_321.bin b/params_shard_321.bin new file mode 100644 index 0000000000000000000000000000000000000000..3c296429540970f4789460623d353b8665f7c4f4 --- /dev/null +++ b/params_shard_321.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17091d12e635a583b063ee450047ef9866165a56f9bd26ee84dd09f0e83cfa1c +size 41943040 diff --git a/params_shard_322.bin b/params_shard_322.bin new file mode 100644 index 0000000000000000000000000000000000000000..409bf6373f7cf0bf8f819cfce3fd9a28c5eaea92 --- /dev/null +++ b/params_shard_322.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af47da8cc605570c4cae39a1581135db1aec386d489234489be79c2d264d4908 +size 33554432 diff --git a/params_shard_323.bin b/params_shard_323.bin new file mode 100644 index 0000000000000000000000000000000000000000..62743b6b8816d4f3bfee663549cb2aac10091030 --- /dev/null +++ b/params_shard_323.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5f7d7b8e4d817047f8fcfdbe8d1fc5817d438038fbe3eecaff66f56b9cccb0 +size 117440512 diff --git a/params_shard_324.bin b/params_shard_324.bin new file mode 100644 index 0000000000000000000000000000000000000000..b022be2d59a6b753c03b799096e8a9a007de7d00 --- /dev/null +++ b/params_shard_324.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d14638a7c44a1c2bc054be3d85979a3cf553870d398c35dfa71782c0859676fe +size 234881024 diff --git a/params_shard_325.bin b/params_shard_325.bin new file mode 100644 index 0000000000000000000000000000000000000000..70ef0e8efd89ea7d3e05389a62ce3152b4c739d7 --- /dev/null +++ b/params_shard_325.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af1efad709d61c079e18f01f764c28bdbde83556496636e5d2e83fc9d63c4ef +size 31522816 diff --git a/params_shard_326.bin b/params_shard_326.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e4dd8eb3319f291b2d1d29cd18246fab0c27651 --- /dev/null +++ b/params_shard_326.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23fd9a13059cf27235f745cd11166c8c3b43c07720b25f24e8c904911f37f8da +size 117440512 diff --git a/params_shard_327.bin b/params_shard_327.bin new file mode 100644 index 0000000000000000000000000000000000000000..19e33d09702bbc45874d54b3fc683f998a9a8c68 --- /dev/null +++ b/params_shard_327.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2baab6d1d6c60c6f0dbbbffd4662b05c60a1af6c4e12ae4eef02eeb61933b4d0 +size 234881024 diff --git a/params_shard_328.bin b/params_shard_328.bin new file mode 100644 index 0000000000000000000000000000000000000000..39642436da0dbabff96ab3c9912a4b7dd991cf13 --- /dev/null +++ b/params_shard_328.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752dcf35efd96cb6d5e7549578f3f3f8ff9052d646f947c841a83360b72caa76 +size 41943040 diff --git a/params_shard_329.bin b/params_shard_329.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f02aa33f6cdb80a3f949502731173b7f569b100 --- /dev/null +++ b/params_shard_329.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb8b8dbe43bfc061993157dd4294e24143ae1d0e510094ab143f2e23a69cf996 +size 33554432 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..72fc91bc7b7318ee8d005cca277f12ab6cd3fe33 --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315e10786ed57973c9d96d43390784fb460d3f26521b1bf74e1b4258e0cc34a3 +size 33554432 diff --git a/params_shard_330.bin b/params_shard_330.bin new file mode 100644 index 0000000000000000000000000000000000000000..afb66f89f7da27978766ff7cf9b99d8761d0a014 --- /dev/null +++ b/params_shard_330.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1b091fe633adefba49b76f69142754a1eac53ea8559079b9699e6a4fd7e921 +size 117440512 diff --git a/params_shard_331.bin b/params_shard_331.bin new file mode 100644 index 0000000000000000000000000000000000000000..8fdbb3105011b93697a29532b68f776cf4671667 --- /dev/null +++ b/params_shard_331.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a602e0bdaa50d51bd68c862f52c1693be23c00b4b80ca8369188d67173c5dd +size 234881024 diff --git a/params_shard_332.bin b/params_shard_332.bin new file mode 100644 index 0000000000000000000000000000000000000000..ff019a2b662fcd4b4a208037128816b251b81e97 --- /dev/null +++ b/params_shard_332.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643487a063819614628ab98ab76c1b9f401f8a2cae1198ba7fbd6d0771d338cc +size 41943040 diff --git a/params_shard_333.bin b/params_shard_333.bin new file mode 100644 index 0000000000000000000000000000000000000000..015b6016e343d8580f10e6e593b6428d4fb30e6d --- /dev/null +++ b/params_shard_333.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3525614e32bdecbed1ced825790dc092e38cdca302709d656f2a144b6a144278 +size 33554432 diff --git a/params_shard_334.bin b/params_shard_334.bin new file mode 100644 index 0000000000000000000000000000000000000000..ca519c72e85f1165ac3ba6bcaddc803291b26331 --- /dev/null +++ b/params_shard_334.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fee5b59257ea4f7e29d52a0631dce01a503e6d34ffe01ed9e730e8148495b2e +size 33112064 diff --git a/params_shard_335.bin b/params_shard_335.bin new file mode 100644 index 0000000000000000000000000000000000000000..26558c7051e40c80a5139b4097e9008b836123c9 --- /dev/null +++ b/params_shard_335.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0831e04edb1291427897752c5aee45e3afc0b36ab7793ee845dc186778c2dec7 +size 41943040 diff --git a/params_shard_336.bin b/params_shard_336.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5690a90db693347885a7e9a1761ec571f96818a --- /dev/null +++ b/params_shard_336.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020bef1f0a971374c55b99fcc30175806141ea1814ceda3642ae847637fb9382 +size 117440512 diff --git a/params_shard_337.bin b/params_shard_337.bin new file mode 100644 index 0000000000000000000000000000000000000000..423c050d8af6f2a759347adae6c63ac3116831e4 --- /dev/null +++ b/params_shard_337.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0bdb42ce91675a3dd5a0df1ce9f0e065d0e3dba86a8d0853f5d40d71ef4cf5 +size 234881024 diff --git a/params_shard_338.bin b/params_shard_338.bin new file mode 100644 index 0000000000000000000000000000000000000000..01d5add4b388aae0614b71d67fe06dbfd511011f --- /dev/null +++ b/params_shard_338.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83140b7a9aed874040e73b88d3433878b92512f56c01597f61ea9e626d6dd448 +size 33554432 diff --git a/params_shard_339.bin b/params_shard_339.bin new file mode 100644 index 0000000000000000000000000000000000000000..68b076f7d8bc8057609f7285f70f6a63ffc0d5c3 --- /dev/null +++ b/params_shard_339.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a60765232d7d058d7fad77927811d5b7f7b45dd7343208a7e502b97f1ba640 +size 117440512 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..35cd22a017610203808913c88f8648e1dcfb3369 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3cbe6201701e70fa1186ec39f76b1aedfd78868fd99fd36133a12f64fcb268a +size 117440512 diff --git a/params_shard_340.bin b/params_shard_340.bin new file mode 100644 index 0000000000000000000000000000000000000000..96b6e597c545eed54355d920a90cd62fd9c9a51d --- /dev/null +++ b/params_shard_340.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:044ce432d90b141e30d4cc3f4bd27a58b8fef64e85573f56fda321f6651d9da6 +size 234881024 diff --git a/params_shard_341.bin b/params_shard_341.bin new file mode 100644 index 0000000000000000000000000000000000000000..4404010f927f5e91646ae659fa55ae28b60ff8cb --- /dev/null +++ b/params_shard_341.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5725d07eefe32b5b09762411ef9cd716d7fe9dee2ee977ccd0cd1e65451fadf8 +size 41943040 diff --git a/params_shard_342.bin b/params_shard_342.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6aee67082c631c54f456379dc5efe42d50d01c0 --- /dev/null +++ b/params_shard_342.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6c050d5aa12ff2f3dcd157f7be472780e6c5a3c956eb06bd0eed56ca3199d4 +size 33554432 diff --git a/params_shard_343.bin b/params_shard_343.bin new file mode 100644 index 0000000000000000000000000000000000000000..612698f8cfb14a5a9fed75674794e1e9da120495 --- /dev/null +++ b/params_shard_343.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a16e0546a420102769b671448b215cc3a05accfd5250a77275de9c97cc36922 +size 117440512 diff --git a/params_shard_344.bin b/params_shard_344.bin new file mode 100644 index 0000000000000000000000000000000000000000..24ffef2772730759f483fce665817b8f828ba24f --- /dev/null +++ b/params_shard_344.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762bcb2dbebaca21bb8fae1991acd250d618935f963213539161f6142ea219be +size 234881024 diff --git a/params_shard_345.bin b/params_shard_345.bin new file mode 100644 index 0000000000000000000000000000000000000000..c441261f2b5d256dc95086a92c13963190618996 --- /dev/null +++ b/params_shard_345.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539499977a82376d1b269647ae1f9b2b54c5a2d9d45af8f4bfb9a7e0a8512c30 +size 31522816 diff --git a/params_shard_346.bin b/params_shard_346.bin new file mode 100644 index 0000000000000000000000000000000000000000..53eef823e6c33c55be6b780afc8402da3b7d3090 --- /dev/null +++ b/params_shard_346.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d81f800fb58586005c1ec396cc6c02114240b8c86f9ce42f90377af0dc955d67 +size 41943040 diff --git a/params_shard_347.bin b/params_shard_347.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c1e9de84007ac08d96dd9662ae318e5c49501c3 --- /dev/null +++ b/params_shard_347.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bddca243a6096e0325699ab41ed290a93925093d801944d67da511060ac0269 +size 33554432 diff --git a/params_shard_348.bin b/params_shard_348.bin new file mode 100644 index 0000000000000000000000000000000000000000..20015e368aaa7e141e24251032306ae46eb024c2 --- /dev/null +++ b/params_shard_348.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f15dddf03aa5bc3668378a5bc2a992c2ffd2990100a436e32dc38473374d046 +size 117440512 diff --git a/params_shard_349.bin b/params_shard_349.bin new file mode 100644 index 0000000000000000000000000000000000000000..df3729455a41fa5c1e6227a51461358b096bdb84 --- /dev/null +++ b/params_shard_349.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a16bc6bfe2c4a08dbe487180111c8b5c2b7037f3f9b20725fe1c7cc91306fb4 +size 234881024 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1513f1a19da84d14eb8e6f318caedacc7dbbc2a --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731ea0c2a8f3898f2ae04a8c036b3b9cd3a1eed925a5ac28191d2fc13d63b639 +size 234881024 diff --git a/params_shard_350.bin b/params_shard_350.bin new file mode 100644 index 0000000000000000000000000000000000000000..b3b363213089260efeb8800ba1a985bdce13ea61 --- /dev/null +++ b/params_shard_350.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a83cc4537bdc030c127f3e96c29d32a123a5eb7d15117e484f7778cd45b4a1 +size 41943040 diff --git a/params_shard_351.bin b/params_shard_351.bin new file mode 100644 index 0000000000000000000000000000000000000000..f57345b60afabd3dd4934a0d49d609f9c64ff899 --- /dev/null +++ b/params_shard_351.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5704c2ee32352b699814b867f071817c7ee1db3df31b42fb7c42044bfd1707ff +size 33554432 diff --git a/params_shard_352.bin b/params_shard_352.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecddf7768ae7625a203b4ceca60ab8c1bd5e32ca --- /dev/null +++ b/params_shard_352.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5755f56a6a3c25ca74ebd69623da16f99dfa868aa3553c45a1d4d51a72c4b03a +size 117440512 diff --git a/params_shard_353.bin b/params_shard_353.bin new file mode 100644 index 0000000000000000000000000000000000000000..208188d706ad77a89e668c383ee96390bda77cee --- /dev/null +++ b/params_shard_353.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb82677dce4deadfa95db59c229fbe4758e63e189cb3d65ca673bdec1303df0 +size 234881024 diff --git a/params_shard_354.bin b/params_shard_354.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e6e7fc09f76670a754367e90f2965d0f73d35f0 --- /dev/null +++ b/params_shard_354.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc38f05db9b3a376b62972bf6e64184e2cbd01574ed9d6c805c3299e3dd2e7d8 +size 26820608 diff --git a/params_shard_355.bin b/params_shard_355.bin new file mode 100644 index 0000000000000000000000000000000000000000..d7fca1887c4a42908fb4369c9e5352fa67b519e4 --- /dev/null +++ b/params_shard_355.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b506611d8bb4bdfbba24c239a0f70ce0150530ac0f22c74ec58420b078eefded +size 41943040 diff --git a/params_shard_356.bin b/params_shard_356.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ac231b4020d71df3f8c7f0274a78cc8f5598f84 --- /dev/null +++ b/params_shard_356.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa715e412450e9ade5f1e3f25becd3e4c2fbf791bc303f91d803f2b0abe61d1 +size 33554432 diff --git a/params_shard_357.bin b/params_shard_357.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a44ca6acf2119fcb04522c01e1112b3132e27b4 --- /dev/null +++ b/params_shard_357.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5535a0fc05e07cb31a2049f965ffb79e2be751f3331bd894a6c64fdc99e3af90 +size 41943040 diff --git a/params_shard_358.bin b/params_shard_358.bin new file mode 100644 index 0000000000000000000000000000000000000000..e23523a397dcc1b2105473e1ca27a92ba2f4d048 --- /dev/null +++ b/params_shard_358.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54933f833459d4cdc955e7e1b2ab010a7587f727ac9af52c4009f2991ba39c0f +size 33554432 diff --git a/params_shard_359.bin b/params_shard_359.bin new file mode 100644 index 0000000000000000000000000000000000000000..12a012247513c079ee6a173e4a1d1187172e853b --- /dev/null +++ b/params_shard_359.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c9c2149d79d83d6f9ab61686b70f5327f8ae563f0ecacf71ba59e16b8d69245 +size 12075008 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..842e9fedb2aa8168c52e5336fa7869bc65546efe --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d2a0c567ba453c0a01526076cf1fd3f1eebae98214ad83ac76885cb840cc2b4 +size 41943040 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..04872da8c3d67b8552579099de98801a0af512c0 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce2ce38d9ebd05a128dc687a7493be3c6f2c6a458b99ec82042b01930dd5697 +size 33554432 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..cf6644cff1176a70e9cc37bcfe3ffd10322981b9 --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7834d3d72ee06fba9ff13e3fac0d0a88b5264dd7d16f8247e1c74c8b08bff5bc +size 234881024 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..19266975212827d8eccad06628220966310b9995 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7250c2f181c500012376f69c02624bf2b1846fe1da301136117f7a8d51dfc81d +size 41943040 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..25c62790af750273c29c24968f3b14270c19508e --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61038e781f8479ab304d86a144366ebc7f84fc66f50bf229c483c573e72c899 +size 234881024 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..ffbed89490ecb2f9c0ad104b7b5af77a396c8a9a --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db8513ad660da78fa54d6a80c1e4149c76da59833f1f20bd72922c48e86b2d05 +size 33554432 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..a0091fe55c600473bfb1f1538251a35898180bc9 --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a93cc33f5072aa460d5511c7461dd7088421deaa8ce3d30d67df852770caf0 +size 234881024 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..0c3e10d117c6de9832ce933587804f59437d0917 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9940be87f17e31da85010023d9be10ed0e8cad4ab6263755953d1f41638b67d +size 32833536 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..914917b64408777a1bf226aa811282d754dd9e80 --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5677215e02e98643211ebc9d60dffbdada9abb28db52b9eaa8ad8cd572c4232f +size 117440512 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..9c75f1fe8975b704d68168e96dea3b359b200355 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66fd391d2b1562e64530f6becdc22100cfd443e9dfb9d16ce073c044fe6f11d0 +size 117440512 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..cdf17861de9a17fa710ad10e698f35047a463c6d --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f44f2cca8faacb6bfda6d9506a165c1c8cd385d07202021abc41afa1f1eb60c +size 234881024 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..62895f9122313a544669b0bc2326c1632da0d893 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8bfe7682a645243712bc382c3e40d929c488c14607c7f54b9bcf566220e3b16 +size 41943040 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c185cf689ea75744206c709b8a97f6e7e1c76eb --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a3817463232ad225cbcf1ec6a234b0fd241da3399529b6a7ebde0a9db98e79 +size 33554432 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..8b9b1c2b095a01d36a695ae19efc99611aeb13e7 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37bcc6ee40ceb3bb80644ecd007f8f154129fee12dd8812c24b2d718d51cfe7c +size 117440512 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..c1eb08435d61c1e5510cc79f5370fca22ea13cf9 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de26238a77933ba6ae2d7607a5b404332d21f809ae5874926cf19992afaf11e4 +size 234881024 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..4ca54e078bd08badb7674db167767e58806e1de2 --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6822c89077fb519d45f1b099be52b7905e39c04aee15c103c0f570ac0b9aaa +size 31145984 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..4bc17190f1359465fb62cd4f45608786e7094c2e --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da2cdfed63eee5894157f41f8cba4c124de9ab8f2c673408e060e72f55a4156 +size 28147712 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..0bc57365554a7f85ca12099d8a61b8b231a25ff6 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47dde472e9978f9e0c33056bdfbf52450584554d703f90b6aa68c554f86111d1 +size 41943040 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..58049cef50c4d1e42e9a04981abc06feb2feccc6 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839a01f6373ae3ac31c3a7bad5a5c266478ea648776c57891da443c42d459908 +size 33554432 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..3034ca789397e324e46f39eb7f8a18a09b5fea85 --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b001e825eeb84343191ed1aae6d9bbef2c2f9bc46e9a3effefa44746933fcd1c +size 41943040 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c2cbd0838fe677c1cca0464d130909e5ba424f8 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7727fd4b288e690ed1b5f2162efaf14460847c8ae1d04dec4a906fc3442ebba4 +size 33554432 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..25455206ae78ce6f94959c00263a10984b65b838 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbdf4ec953742af83bdb14fa50b0f2d0cee8a88f97565877afd1e50c56d3a782 +size 117440512 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b427426de837f36ea6171e409e307a2e6410c03 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df17b50730d91a996bef99bb1331e8e6bc0b16644c8c50ad381159a09a5670d +size 234881024 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab1511592d4c906550e3a0abd448de581404adf9 --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e5bfdbaa46a7b600acae34e370cfd338e8a19f8f48a3043e0d7ec073c0d54b +size 117440512 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..91323fd393bb14afa20e60dace3da3ddb152d0f6 --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff6b6c2f6158a1002687e65e223b7d758768da54bbdfdcc9205bd547fa519a2 +size 234881024 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..b21a7636d9181e28b3c972e75885171feea14146 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a17732a1ebdd183dc17f64c4776da0706e9f6e2898b54a585e8b2a87d4a1b6 +size 26804224 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a7695b6c534a107e5ef58c7abc80ff2d8188ace --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa823d598c3ae03349fc4a3dde2e4f41c1cd058024def320f15ddb55d95fb02 +size 41943040 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..400a79ea1b6899b34f1e2debc148ba4be6394e5a --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba17610b66b4d076039c0b314a7fa6592e1aea01cd4c830236d82c5d2b939aa +size 41943040 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..fdd1fe8e2584fff7faf5440eb00cd873ad687c6e --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c34ec806f03935df3bbc4384a576b9504242b5c7e72c7c374dc70be7a54cd5 +size 33554432 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7be311d7b03afebbf4a1b0d94349b7d7e51edb4 --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86415e8d068f2c59b299ef72fd1762f6e8d09f902de3c00eee140e468a8b79a5 +size 117440512 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a4baea2d82a2bc38e2b5ddebf35a8a820ad238e --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3297cd4ea00246e883ddeb266290b64f49d123ef257a1c3ae1ee56eae63d16dc +size 234881024 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..cea4dddba30e9cdffca5ad614444c46303479fc0 --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249f774278ff526c19202d7fbab2ee653fc5b7cdcc71a306040582448a78c8a4 +size 41943040 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..519050581713b77c6ccbef936b73ee660fd1092d --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a591620e50988c1c7075c694c42c1d37d859c77019e089f341e8b98c467a0190 +size 33554432 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ae487f14348e2f2348bf85c0354a76d06914d47 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b939fa40ce573df391981dc8082cb13d574afcecb771206cd1f1c8acadae5f34 +size 41943040 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..46c582d5f9a7d0b5926ff82dc95dca024505f4a9 --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ad5ef66dcbc4f41af93ea6d9b2a6eb278ce3c89e82a9ebbdc81fec8a0fdefa +size 117440512 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..53c349b57a1bd694bbbb9b6f9b0541cbd65a9d42 --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9a4c2343c8abd1e82fc492506c3a25f47aa4c0a141349c2aba01b70ac17e8e +size 234881024 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..4e7409582bfae0fe609f9f309ef0f1599ee949ce --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0631b5d7b66252b1f535456d36572ffbb360d97a006e0eaf35effe3093f5fdbc +size 28114944 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..17580d3ca2cce926c1d5d4cde3c74ad28673f4bd --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf38bde4ff62193531be0a74bbdd3038214091e73ac79efcbe851d4e155ca6f4 +size 33554432 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f028a6dcf81437058ece9f240be7ef2c9227073 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365d563e9efabb618b68c693f5d9f4ab02610267a5bf1786e01016d476e75d7d +size 33554432 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..4111218e0c233ef1f2dbb3e0ff81ab0cbc156e5e --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cadb7e16668b7c7c53e50b6cf16184db0dd3f3192572d2288e62089e7383bac0 +size 117440512 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a357276f04f975d103200b382c594bc2e1140d9 --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0828c7f3a9d850313d5e31618bcd8eda84f75ede7861762e5c5875a105ae9f +size 234881024 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..08a9c0209bccf2231d07a46de12725960ae80498 --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7386e208dffa79303044bec012ef58ace6e80e5ea5c6c2fe352598dda1afa4d +size 41943040 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..450fdad7c782625fc0297c3f3caf149f7309fe26 --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebee582d1b14cccf2832054836c55f87ff929489430225abc55b0a46d0f2296 +size 33554432 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..d829585ce4bb0429d82c7b5943fd28134f73c563 --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfef999f0115f07162d200dbd011811c4c9eef97677ff616a0d039c8a8cbefb8 +size 117440512 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..fae474d619691b400658dbe8d9d216109cd84b99 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f2e992fdafc7992a7d831645de420415654cecf476516180260f8ee917a015 +size 234881024 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..052710d5be6797a03f5043ec34049b00110d1b4c --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64ea80ecb35427fcb0d2db4df419903da390928a2d118f332cb976a18ec5cc5 +size 41943040 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..de508d3a8b0ed81da2d18c4a398b4ce784400923 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93a146e0a38eb2b5fe07a2021cf2c98152b236cbb8e231b339fea2ed4e53e30f +size 32817152 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..360537bc21af8660c0b2b96fbb83b7b2abd5795c --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11de3008b21c29c3d3a80b79c74ca14e50caff4d60dfe6c31be8ddca633baa61 +size 33554432 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..53fa5e9923cdd572fdc1e448340eff35fd1faf9b --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b5f95993582600de185b2b88b5bfa17b0e608c02e83881332010826e1ee52e +size 525336576 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..41969bd4cb3e46109accbb572057a69387a4a05c --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8afc91bd07e6786f27a13a682350a07a8df364292c43ac2a75747bda06eb9e0a +size 117440512 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..3342b121659a27556ffccdf320ba9c9f97c80c36 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13fa6f96e503a0cd180dc5b19a6b6fc59c73c9bb0c9f5557c7ebf38146b4492 +size 234881024 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..98991fcd3f597bcc8a69b20e1c6f6c090a28b39e --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:823534a0582d721005ff5d53e4bbfeaef19f9671965c3461c0ef951431dbf296 +size 41943040 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce6da2eb182b838d6b6d424081e8f8c0047262e9 --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:024632437f42e8b71707809cfb12f468146c800586c365a3370e711f0c451e67 +size 33554432 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a2b23d168a182b89ca49c5c4eb641f257224ca0 --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3888e0785e294b20d166e1cc7f7ad17c1572f0e3536c0cc92ed6645bf810555 +size 117440512 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ebf7907e589e9b0f4580d657d5fefe0c3ba1565 --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75382f50ed16caa923b96f8eeb6febc625c4a73f49e732f245d9492c0f3dfd3f +size 234881024 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5502924b7de44598994e4a5e22a99a90d9fe2b0 --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bba727b6909e47c3d01892fdf1d7dba533d937cf4f80d2c61cc7e79e8ae6488 +size 41943040 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b080b032e6f3c20ab43c0221bc8f7a0c9897882 --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae15c910c1b3e30e85aefb47a71329f9ac8f270ca00d85650c7400bd04c3869 +size 33554432 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..1125de60a3e702261286d513d7d2769a8acce4d4 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b81c5a7d150fa87cba495d054018506ab8d4e623b026a8988fbb20a1f2c986 +size 234881024 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..d2d05f15950188fd8516e5444056ac08910ebc87 --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc0950456b87c85dc8ebf1a3801048aec2e5f868e28e2caa34566b32708d13f +size 29196288 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..dcdc6e8bcc65df7caaf40455a82bc810b3ae48bf --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28ceb477545b048a6a1e2805bab84269e0126a4613bc4a3817808e8c0c056fb +size 117440512 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..7e60b71b77c8c5aa9cf38c616305dd26a28cd353 --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e60b533d96a8d66259c9100a7477583da560373e57d31eb17487d88cb71b8325 +size 41943040 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..3209a59940a3d6aeba8dea0ee47cff86423a85e1 --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4549c7de89945e88fd0593b258055c470532f2803bb4886a0c07bf75fd13960 +size 33554432 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..f36cf4aadb9986d92f9ed95fa40350de7fd6e3fd --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f7eb304a6e47b6046f7b0d2557eb3c353132098a22718bd5e7e9c9d7da3399 +size 117440512 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..b6e90c963ee53d5d040bab01b7b28b4417bf4773 --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9c6c3531ce5c99807d83e122193b45b5079cec930719f8846543991955871c0 +size 117440512 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..d04f1a9873cb020a59d7473f979d4b816afff301 --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eda23850f5728e53a87c077a9a6ddb50dfb6ce4666b83520e3d32e4c00c2804 +size 234881024 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..912efb6d53a6a25a6d6ff1f8f188384a6bee02f7 --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac6d6edac6330e10fd4ad030613c57bc342490a44b59d65046c02ba6d6a4da6 +size 41943040 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc5b5e5cd217087b900541094b031f4cdfb267f3 --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0a10246e5b0cb8f8582d1ff0264dfb78ed4f4b6b6c4cea293feec44eb24d3f +size 33554432 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..484f98a2cd3d91ba4ebeb9a0e0ecefdced32a03c --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1bc80dfef10ad3beaeac8c901821e1283dcb9fafa0239247cbbac9cda88a269 +size 117440512 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2fafec0a15be017ef2c3804753c555689c41ed7 --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2083e889030e3cc759fcdde740ea489ed2bd204a465f4407e9d21309cdc152 +size 234881024 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..07fe08b18eca9f5dadd5e95321a9b86ad7232c41 --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952ea4ec3b386e564ef0ead14074780a3312889451f3b86ed7fb756a6e3f77c9 +size 30490624 diff --git a/private-llm-config.json b/private-llm-config.json new file mode 100644 index 0000000000000000000000000000000000000000..7eceb98a54a6b78825fe55a94919a9196dd70530 --- /dev/null +++ b/private-llm-config.json @@ -0,0 +1,51 @@ +{ + "model_type": "llama", + "quantization": "w4a16g128sym", + "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 +}