| { |
| "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": "e43d79f32d3b5a843d16b885116e69de" |
| }, |
| { |
| "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": "202d1b8be586f2f3ca229dd85d93f5b2" |
| }, |
| { |
| "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": "d4921a244f52ac41d140a0348d8c77c8" |
| }, |
| { |
| "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": "88d3d7425047fc176a24b259fd882fe6" |
| }, |
| { |
| "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": "cdea2fdcdcdc40b51b0b5d4fc9011bd6" |
| }, |
| { |
| "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": "e35d61b26eb878e6ee4e5995e4332a27" |
| }, |
| { |
| "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": "2efa812f4dd870bf48e0887755e43aab" |
| }, |
| { |
| "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": "c74b4978ec89e62ebea809dded41c5bb" |
| }, |
| { |
| "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": "9b072c268227d949a11ac92ad50794c8" |
| }, |
| { |
| "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": "bf3539e126eb17dc34c13aa75e5c36b4" |
| }, |
| { |
| "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": "36ff00813b92dc3e6db718a5dd607535" |
| }, |
| { |
| "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": "f3b6152fa00906afc6af1f7bde9496d6" |
| }, |
| { |
| "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": "4ebc985112a8a9f275e4ea024760f4b7" |
| }, |
| { |
| "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": "4b658a70842aaab0d569224130b6475a" |
| }, |
| { |
| "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": "654d80c705512143b15e59b4dfef5994" |
| }, |
| { |
| "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": "6e4b1d539a3c3a905833652cfb76548f" |
| }, |
| { |
| "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": "c5c180e57d5282bc8b4a85f2a99c42af" |
| }, |
| { |
| "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": "137470ced56111c336d9a72c2c16349a" |
| }, |
| { |
| "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": "926f85174a7bdda9cc81340e81f07c21" |
| }, |
| { |
| "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": "11183d8284a8c4dd3fb9aa9575161af4" |
| }, |
| { |
| "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": "7d5f77aa0212fd4ca2d99ef307ae1828" |
| }, |
| { |
| "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": "472a5e9404cc3d2da5bce1191c3e4e74" |
| }, |
| { |
| "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": "23c04fa418cbb30787beaaf432a33d6a" |
| }, |
| { |
| "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": "379b35af828d4cdee9b2e2fcf5414587" |
| }, |
| { |
| "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": "a472e70ebec1ad140877528430307737" |
| }, |
| { |
| "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": "44b582eaff64326af86dfb3b549389c4" |
| }, |
| { |
| "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": "490d27cc22bdd7cb5f6f21dd2e653ddd" |
| }, |
| { |
| "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": "bc3641b77c8183b729b673da20cb3868" |
| }, |
| { |
| "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": "e59f8699e1f82d97761f18319ae51093" |
| }, |
| { |
| "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": "16f3fffe3bfcc167ec8d62371ab4c360" |
| } |
| ] |
| } |
