| { | |
| "metadata": { | |
| "ParamSize": 98, | |
| "ParamBytes": 2471628800.0, | |
| "BitsPerParam": 16.0 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 525336576, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.weight", | |
| "shape": [ | |
| 128256, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 525336576, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5fe6bfddebce8d7687658d3fbaa5a3bb" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "649a3faa52ddd6011b5bf890357144d7" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a146ea08e79066f263468617118d49af" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4773b047a56a813abc31d78bc7ea458b" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "757e94d880a0af3916245d1abf2f0cc9" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20987904, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 4096 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 8192 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12591104 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20979712 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20983808 | |
| } | |
| ], | |
| "md5sum": "9c81d34101a3a6d5e083c9294d6c072e" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "72c909870f091d2288d5f1bbf14227a7" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "17d7431f3e56f56b8a4bff1c4ba21b16" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "307158910e9ffcdbea5f1c0fe216793a" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5fb14051ac92a7a55be71a22fff7cd3d" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4df532c18c7c8f280a7586515c561e99" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "039b13862f3f7164be75f5b572aa4228" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c0438cb3f6fc4377f810b81e1bd007c1" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5fd85ab93fe4184608a942ff68c831d5" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "ebdea31540cce36afe9450214d1bfd3d" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9d302afd4a80e8a0548c36f3991d9ad5" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cad57947b90650ef9d736f7a55790e9f" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "66158059d9c393abcac5586ac8de7cf1" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0c8824c203e4055c1d1540faab369234" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "317da7cb6758a90a6c45d597e278e5d1" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "6c577fbecc01f72992423567b0bd1481" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7ec87a42eb0dc91c9813a4e012b20c2f" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "70f847da51c9aec779ef299f8077afb4" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "6026821264760d740b1409c0bffa1deb" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "39d8449ebda4b408ee6959645b49994f" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "807a9c5343769339cb9624ae75ed216a" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "77329a20b587c214dd987314bdfead17" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "38a444decbac4826f46fcfe12380e15e" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0f07125504c8a77b1cc9f36cdb0b8022" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "2d1357a7be66e40adb43693a389f015e" | |
| }, | |
| { | |
| "dataPath": "params_shard_30.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4a2a4bb5a43a017cba209f668cd87347" | |
| }, | |
| { | |
| "dataPath": "params_shard_31.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e862a436e391ac68e461ef9667250725" | |
| }, | |
| { | |
| "dataPath": "params_shard_32.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "e59f320408694ca1caca6b143ad0d63e" | |
| }, | |
| { | |
| "dataPath": "params_shard_33.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f1f7264cb6daee8fadf650ffe5483d85" | |
| }, | |
| { | |
| "dataPath": "params_shard_34.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c128f1b4cdcbee7d1fe0c440478735fa" | |
| }, | |
| { | |
| "dataPath": "params_shard_35.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "0a61d05b6358398e961f11da4841ebf7" | |
| }, | |
| { | |
| "dataPath": "params_shard_36.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7d96d469a438acd143d71bdb8ae11053" | |
| }, | |
| { | |
| "dataPath": "params_shard_37.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "940d4b77e813c39131c8b190a96afbdc" | |
| }, | |
| { | |
| "dataPath": "params_shard_38.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "d1c8264837f5511329f39ef0c5e12cca" | |
| }, | |
| { | |
| "dataPath": "params_shard_39.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6b6ba1195aa2a5d584dbf22d96cbc780" | |
| }, | |
| { | |
| "dataPath": "params_shard_40.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0fe783a7fa4365570b61f40b1d02e992" | |
| }, | |
| { | |
| "dataPath": "params_shard_41.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "3d5c6266a9e3be363d7b1636aed7acab" | |
| }, | |
| { | |
| "dataPath": "params_shard_42.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6528032fc98667817d9bc4f8e22a778f" | |
| }, | |
| { | |
| "dataPath": "params_shard_43.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f8f919204af1a388d05201e6c2964dd2" | |
| }, | |
| { | |
| "dataPath": "params_shard_44.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "81b962b29fa9e116e8d210f867f356b7" | |
| }, | |
| { | |
| "dataPath": "params_shard_45.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 8192 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "29e8087714358ca3b41b85046a80c13d" | |
| }, | |
| { | |
| "dataPath": "params_shard_46.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67108864, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67108864, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d56e3e4e2fb83591eeeacad6fa10e9e9" | |
| }, | |
| { | |
| "dataPath": "params_shard_47.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20979712, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20975616 | |
| } | |
| ], | |
| "md5sum": "50b62008e92be3380dbc8b46c48828d2" | |
| }, | |
| { | |
| "dataPath": "params_shard_48.bin", | |
| "format": "raw-shard", | |
| "nbytes": 20975616, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 12582912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2048, | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8388608, | |
| "byteOffset": 12582912 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 20971520 | |
| } | |
| ], | |
| "md5sum": "bdbdfa1c75499c5c12840c1a685e2f44" | |
| } | |
| ] | |
| } |