| { |
| "metadata": { |
| "ParamSize": 311, |
| "ParamBytes": 868547584.0, |
| "BitsPerParam": 4.501079412165634 |
| }, |
| "records": [ |
| { |
| "dataPath": "params_shard_0.bin", |
| "format": "raw-shard", |
| "nbytes": 116686848, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_weight", |
| "shape": [ |
| 151936, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 116686848, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f12643ff5b8191ba45c12306ffeaf3f6" |
| }, |
| { |
| "dataPath": "params_shard_1.bin", |
| "format": "raw-shard", |
| "nbytes": 22330368, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_scale", |
| "shape": [ |
| 151936, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 14585856, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.0.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 14585856 |
| }, |
| { |
| "name": "model.layers.0.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 14588928 |
| }, |
| { |
| "name": "model.layers.0.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 21470208 |
| } |
| ], |
| "md5sum": "ac267ddefb0cfe8f3d05ee274f19fe95" |
| }, |
| { |
| "dataPath": "params_shard_2.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.0.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.0.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.0.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.0.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.1.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.1.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.1.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "3b98b5d949ad8d8b96a57824eb180d56" |
| }, |
| { |
| "dataPath": "params_shard_3.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.1.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.1.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.1.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.1.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.10.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.10.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.10.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "ea6a49f202b82d90f74669f0cc3b1a6e" |
| }, |
| { |
| "dataPath": "params_shard_4.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.10.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.10.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.10.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.10.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.11.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.11.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.11.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "6f4c1c83e0b93376a6a959b04dcbd030" |
| }, |
| { |
| "dataPath": "params_shard_5.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.11.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.11.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.11.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.11.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.12.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.12.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.12.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "4bed620d80baf7a625b4f2b55720d1ed" |
| }, |
| { |
| "dataPath": "params_shard_6.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.12.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.12.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.12.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.12.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.13.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.13.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.13.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "2ee2fe7ed36ea8f1002010077b9df783" |
| }, |
| { |
| "dataPath": "params_shard_7.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.13.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.13.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.13.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.13.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.14.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.14.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.14.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "aff97a058fe9834daf7dfdcc54ce1290" |
| }, |
| { |
| "dataPath": "params_shard_8.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.14.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.14.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.14.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.14.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.15.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.15.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.15.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "e7c4e94a8036f292aaed181e6edc09d7" |
| }, |
| { |
| "dataPath": "params_shard_9.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.15.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.15.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.15.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.15.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.16.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.16.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.16.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "ca8acc94f0a073872e4c57ca82d194c7" |
| }, |
| { |
| "dataPath": "params_shard_10.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.16.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.16.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.16.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.16.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.17.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.17.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.17.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "23ef0d6bbe6537908ef10745d7802115" |
| }, |
| { |
| "dataPath": "params_shard_11.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.17.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.17.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.17.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.17.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.18.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.18.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.18.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "224e157ef52b61323fc5c2ed033f1788" |
| }, |
| { |
| "dataPath": "params_shard_12.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.18.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.18.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.18.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.18.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.19.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.19.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.19.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "94c81dfefc832bab7b20e27d3c0c8758" |
| }, |
| { |
| "dataPath": "params_shard_13.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.19.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.19.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.19.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.19.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.2.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.2.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.2.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "6c81ba7fc47c325947e7e5106303e32f" |
| }, |
| { |
| "dataPath": "params_shard_14.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.2.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.2.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.2.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.2.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.20.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.20.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.20.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "129f41d63397821c0f63cfd0141f8bed" |
| }, |
| { |
| "dataPath": "params_shard_15.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.20.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.20.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.20.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.20.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.21.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.21.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.21.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "35ba1290121fdf3a1c0b2b58e27c8d8f" |
| }, |
| { |
| "dataPath": "params_shard_16.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.21.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.21.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.21.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.21.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.22.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.22.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.22.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "509dfddac1184902174af47bd1b05721" |
| }, |
| { |
| "dataPath": "params_shard_17.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.22.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.22.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.22.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.22.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.23.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "509256d6fd00a1079cd45cb858e4008a" |
| }, |
| { |
| "dataPath": "params_shard_18.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.23.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.23.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.23.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.23.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.24.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.24.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.24.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "51929070aece3b958dd48704ac0298a7" |
| }, |
| { |
| "dataPath": "params_shard_19.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.24.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.24.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.24.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.24.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.24.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.24.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.24.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.24.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.25.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.25.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.25.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "46f18293ad8ceced92da49d68cda158b" |
| }, |
| { |
| "dataPath": "params_shard_20.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.25.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.25.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.25.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.25.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.25.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.25.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.25.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.25.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.26.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.26.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.26.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "b825d850a1d5fe3b99202009933c2215" |
| }, |
| { |
| "dataPath": "params_shard_21.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.26.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.26.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.26.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.26.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.26.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.26.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.26.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.26.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.27.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.27.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.27.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "d4530d4491856a363a88c0adc1b5791f" |
| }, |
| { |
| "dataPath": "params_shard_22.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.27.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.27.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.27.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.27.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.27.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.27.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.27.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.27.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.3.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.3.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.3.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "4e98aa0eb726f6872531f79652915739" |
| }, |
| { |
| "dataPath": "params_shard_23.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.3.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.3.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.3.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.3.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.4.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.4.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.4.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "ea8c424f56d1de1b5e8653306e79bbb8" |
| }, |
| { |
| "dataPath": "params_shard_24.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.4.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.4.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.4.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.4.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.5.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.5.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.5.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "654a7c55d1a8399b83312640857affb0" |
| }, |
| { |
| "dataPath": "params_shard_25.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.5.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.5.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.5.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.5.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.6.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "955054c36ff15e1066d5644a0019402e" |
| }, |
| { |
| "dataPath": "params_shard_26.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.6.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.6.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.6.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.6.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.7.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.7.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.7.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "c56ae9b14e7c1fe0d904d3762762b3f1" |
| }, |
| { |
| "dataPath": "params_shard_27.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.7.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.7.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.7.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.7.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.8.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.8.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.8.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "f765cbe90b45663002b016ac2f79117c" |
| }, |
| { |
| "dataPath": "params_shard_28.bin", |
| "format": "raw-shard", |
| "nbytes": 26331136, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.8.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.8.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.8.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.8.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.layers.9.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| }, |
| { |
| "name": "model.layers.9.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 1120 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 6881280, |
| "byteOffset": 18589696 |
| }, |
| { |
| "name": "model.layers.9.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 280 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 860160, |
| "byteOffset": 25470976 |
| } |
| ], |
| "md5sum": "409f2550465ed773109c9bbb9c3cfe23" |
| }, |
| { |
| "dataPath": "params_shard_29.bin", |
| "format": "raw-shard", |
| "nbytes": 18589696, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 17920, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 13762560, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 17920, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1720320, |
| "byteOffset": 13762560 |
| }, |
| { |
| "name": "model.layers.9.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.9.self_attn.c_attn.bias", |
| "shape": [ |
| 2048 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 4096, |
| "byteOffset": 15485952 |
| }, |
| { |
| "name": "model.layers.9.self_attn.c_attn.q_weight", |
| "shape": [ |
| 2048, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15490048 |
| }, |
| { |
| "name": "model.layers.9.self_attn.c_attn.q_scale", |
| "shape": [ |
| 2048, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17062912 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1179648, |
| "byteOffset": 17259520 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 48 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 147456, |
| "byteOffset": 18439168 |
| }, |
| { |
| "name": "model.norm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 18586624 |
| } |
| ], |
| "md5sum": "ebcc02b2e24e1ef60106375ed6cda999" |
| } |
| ] |
| } |
