| { |
| "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": "4694e37ebef2d3e5bafb06d82a667e2b" |
| }, |
| { |
| "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": "ed0f6440bb323503587fa0afdbdec092" |
| }, |
| { |
| "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": "781922c1f1dea930c9ace94959513af6" |
| }, |
| { |
| "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": "6594eda9351e352ba13abec4ec2b6993" |
| }, |
| { |
| "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": "df94d33338c34bb07ee63c30478f001b" |
| }, |
| { |
| "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": "e149b836b9a04c03e4e7e5a8d6a07e03" |
| }, |
| { |
| "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": "d146804d873ad01f2edbe2e823ed1547" |
| }, |
| { |
| "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": "0d96c1b2032e753390ac78d4799d4c54" |
| }, |
| { |
| "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": "e4e4183a9100409dc3cc5a909367273f" |
| }, |
| { |
| "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": "7e0d55c9819f438e93e17c89247ef1c1" |
| }, |
| { |
| "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": "b09108902d6caafe01f87058d57881c4" |
| }, |
| { |
| "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": "ee3205d4ce9d18e19ef0bf8fe83faa6a" |
| }, |
| { |
| "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": "3b228b8fbc4c105d3306446318cfbce8" |
| }, |
| { |
| "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": "cb3beb24e3b9884417cad4fd7fe99ed3" |
| }, |
| { |
| "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": "ff9bc14c8df262a8017f41d4ed54d441" |
| }, |
| { |
| "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": "6dc45712a2e4b8b1b2697574287da4be" |
| }, |
| { |
| "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": "a8c2b56aa23d7464deec684f2d0a2bc9" |
| }, |
| { |
| "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": "2a69d95b2ec59c8a79e08d78a92cbae6" |
| }, |
| { |
| "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": "87c0a2ee5a9f25ae1206968abc91792d" |
| }, |
| { |
| "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": "6f2788e24fcdfba1216d2fd24ec362b8" |
| }, |
| { |
| "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": "704aaa7d25fdf7a4cdb704d705863f67" |
| }, |
| { |
| "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": "4055e7fbde63b552d460f7e21b64e53a" |
| }, |
| { |
| "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": "2fc28a9b72690d4968c3b884afd0907f" |
| }, |
| { |
| "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": "4fa5f26714ae0a5589578f5956eff288" |
| }, |
| { |
| "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": "2968d93c08b3df1b557ed9ba13580ba8" |
| }, |
| { |
| "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": "810076920e127e26f0803705e472a0bc" |
| }, |
| { |
| "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": "d9f7e14700e5a8de382cabe90bb42ddc" |
| }, |
| { |
| "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": "96881e4fb558abd04058843c822ec43d" |
| }, |
| { |
| "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": "244138a3ba5259ce76d1b645ce040bf3" |
| }, |
| { |
| "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": "3e193b78c94ac1cdba2a515d97683291" |
| } |
| ] |
| } |
