|
{ |
|
"metadata": { |
|
"ParamSize": 313, |
|
"ParamBytes": 4760885248.0, |
|
"BitsPerParam": 5.0011817065612245 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 272498688, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_weight", |
|
"shape": [ |
|
152064, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 272498688, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "510653a4cc50f6fa6407408fe593d3f0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 34062336, |
|
"records": [ |
|
{ |
|
"name": "lm_head.q_scale", |
|
"shape": [ |
|
152064, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 34062336, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3cf6e86315e40ca815ffbcdd6df900fe" |
|
}, |
|
{ |
|
"dataPath": "params_shard_2.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "415cf091377c59c8e066ce34cad87fc5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6ca48c5544b032d0e51df962fbb560d2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f1489373bfdc1844bc3c0d18b0b78871" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "05fc55cf9b8971f07fab5a240f75ddb2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.bin", |
|
"format": "raw-shard", |
|
"nbytes": 32723968, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 7168 |
|
}, |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 4250624 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 12737536 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 12744704 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 19167232 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 19970048 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 19977216 |
|
}, |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 24220672 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 32707584 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 32714752 |
|
} |
|
], |
|
"md5sum": "2ca5c4bb1177c9b1b601ae07d92973e5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7ca14608dcf3446dc34939109daa5cb0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2e7b1becc450e3318fb795c227fd4b98" |
|
}, |
|
{ |
|
"dataPath": "params_shard_9.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "88fecf91939b086849aac8d69d288bd3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_10.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d88db17bf0b44d67a8c0eb6b74890506" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fe152e83bae5a84f3f260519624d7116" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.22.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.22.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "4d50813ef1b0952b91ca4f5153db06fc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ce237b108acffa35790d4ef186b0affc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d6fd5565b48463982783dc2e94196652" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.23.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.23.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "c1590f9d2c95d719539585074a86323b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_16.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6162af2fe80ff1b3a2aaf3be305fbac2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_17.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0e2dbd64bc347e41e1af74280cae59b5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.24.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.24.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "0e811f1f813352fe695ede58706cca7f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "041cb00d7bf64114470ff2211ca61066" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ee111a82c057e59e1b9ba61c4db3aa29" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.25.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.25.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "a2518cd0d5375a1202fac391ce80ea4e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "851e9565156393e859c8f3751b0635bf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_23.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "38aff0272d9c31b14c76c66d5fcc7cc3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_24.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.26.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.26.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "4387c4d5f45e85e719ee7624aa10924c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_25.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "26e8e1560c817c06eaab4338fe93d88f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_26.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "08c9fc32541dd05d0f78c21e6f8bbe8d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_27.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.27.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.27.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "2e16329b4a94eba16207d5dc84273105" |
|
}, |
|
{ |
|
"dataPath": "params_shard_28.bin", |
|
"format": "raw-shard", |
|
"nbytes": 272498688, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.q_weight", |
|
"shape": [ |
|
152064, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 272498688, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "89dfe76450c674a5125daf56c3acd498" |
|
}, |
|
{ |
|
"dataPath": "params_shard_29.bin", |
|
"format": "raw-shard", |
|
"nbytes": 34062336, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.q_scale", |
|
"shape": [ |
|
152064, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 34062336, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b9e90bf1a497621371e41b6369d0c2a0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_30.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5bbc337c80e44a500ed0ee7e753d7888" |
|
}, |
|
{ |
|
"dataPath": "params_shard_31.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c60caab33946131753bee6793739ce0b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_32.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29276160, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16529408 |
|
}, |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20772864 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29259776 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29266944 |
|
} |
|
], |
|
"md5sum": "b925bedf2364dfeebbfdecaccea2ab69" |
|
}, |
|
{ |
|
"dataPath": "params_shard_33.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "09db6e5cfbf49c1f8648df42ab281d1d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_34.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4e5886bd1c79b624eb6f89644b3f798c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_35.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "581f78f4da3dcc5262ec256c997b021a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_36.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "93a50f1194dfd17a3c626ac68a42693e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_37.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "551910720bd4668ea20f344a5cc0a452" |
|
}, |
|
{ |
|
"dataPath": "params_shard_38.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "10eb1099ba40343370ba992115ae7aed" |
|
}, |
|
{ |
|
"dataPath": "params_shard_39.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5f7195531cb9b4af525d81aea8352de2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_40.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "442792e8264594176fcb5d7049227680" |
|
}, |
|
{ |
|
"dataPath": "params_shard_41.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "40711ac072a631528188d88f49ba9126" |
|
}, |
|
{ |
|
"dataPath": "params_shard_42.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "084dbce4a740aa3783a8d71eed58a15d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_43.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2450c7ee53558583f8ac3f458c439910" |
|
}, |
|
{ |
|
"dataPath": "params_shard_44.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "d41bd9d7020f307c0cf39d2818179b78" |
|
}, |
|
{ |
|
"dataPath": "params_shard_45.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "955074dfff39b1a78f9859095214b3d7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_46.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1582f92630a0b33b6c0f22c6368b01a4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_47.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "013e2e4491feea9063ab544d3cf2ac30" |
|
}, |
|
{ |
|
"dataPath": "params_shard_48.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "40bf232984896547f2c9d5276617b7bc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_49.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "27ad71c3d4ddf73dd864f1ee3b46b37d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_50.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "5d73c4b8eb3900f199da62715988357b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_51.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "add9316d56e97d2ac71821d450b7d518" |
|
}, |
|
{ |
|
"dataPath": "params_shard_52.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c965d6268e3575eba8b9db3fadafa54d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_53.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "c690844c463de56196cb918ea7c9cc64" |
|
}, |
|
{ |
|
"dataPath": "params_shard_54.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c9735f02498340fd3c68e791a6a24b66" |
|
}, |
|
{ |
|
"dataPath": "params_shard_55.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8cf3c5a718e44923f41c8356848c9b59" |
|
}, |
|
{ |
|
"dataPath": "params_shard_56.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "2b86f58d51e5bd735a0e3bdebaf88816" |
|
}, |
|
{ |
|
"dataPath": "params_shard_57.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2990ecf13b020f7d1ce6a57ae3bc7b2c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_58.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "83e89f0247295e37d41adf8a54eb82c2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_59.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "8537883e2ebc5feb60a6247988a6e7e4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_60.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "963cd49bf14ffbf7cedc3311b2448d38" |
|
}, |
|
{ |
|
"dataPath": "params_shard_61.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0dc624a7a0d0172cb319bf44a82c6947" |
|
}, |
|
{ |
|
"dataPath": "params_shard_62.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 16522240 |
|
}, |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 20765696 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 29252608 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 29259776 |
|
} |
|
], |
|
"md5sum": "ccb57b3d01e648bbc931a658838f9e7b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_63.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5d0d1e1f2133e58533dcf81402e4c41e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_64.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8c95fae0058863fee1f6912fe4abe704" |
|
}, |
|
{ |
|
"dataPath": "params_shard_65.bin", |
|
"format": "raw-shard", |
|
"nbytes": 30064640, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 8257536 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 9289728 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 15712256 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 16515072 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 16524288 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 24781824 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 25814016 |
|
}, |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 25821184 |
|
} |
|
], |
|
"md5sum": "95379d0574c73e15dd917fbdbc54c4c0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_66.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "69120ad1870db92ce3e92361b9977951" |
|
}, |
|
{ |
|
"dataPath": "params_shard_67.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "956b7119c6995fc51ca53b046378912f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_68.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 8486912 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 8494080 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 8503296 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 16760832 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 17793024 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 24215552 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 25018368 |
|
}, |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 25025536 |
|
} |
|
], |
|
"md5sum": "13bdebba56cb9aa95e5e2c9a50c71e9e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_69.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "97c546bc5b7beac1fb3375842e879d62" |
|
}, |
|
{ |
|
"dataPath": "params_shard_70.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "555c36b9ec75b3467fd8e9aa77d52f56" |
|
}, |
|
{ |
|
"dataPath": "params_shard_71.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 8486912 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 8494080 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 8503296 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 16760832 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 17793024 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 24215552 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 25018368 |
|
}, |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 25025536 |
|
} |
|
], |
|
"md5sum": "e6a39eb3a717c47d2f18f593e7bb6761" |
|
}, |
|
{ |
|
"dataPath": "params_shard_72.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5c6a305e0c427a01ec6635f7dcde81e5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_73.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "83de4d465eabc78a2013e2bd1e529642" |
|
}, |
|
{ |
|
"dataPath": "params_shard_74.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 8486912 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 8494080 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 8503296 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 16760832 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 17793024 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 24215552 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 25018368 |
|
}, |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 25025536 |
|
} |
|
], |
|
"md5sum": "924e88ef42600b938673703ff90fbd90" |
|
}, |
|
{ |
|
"dataPath": "params_shard_75.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "69f501185d7855e72344a64ae3b15b63" |
|
}, |
|
{ |
|
"dataPath": "params_shard_76.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2529d21261f23702050aabf16647d5c1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_77.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 8486912 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 8494080 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 8503296 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 16760832 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 17793024 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 24215552 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 25018368 |
|
}, |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 25025536 |
|
} |
|
], |
|
"md5sum": "29fa63635d282cf79354353f020093b0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_78.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ac233d327f2c836f0ae9c393c13ba7b1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_79.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7a64e2458c5d41d61728f30553ca06f9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_80.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 8486912 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 8494080 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 8503296 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 16760832 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 17793024 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 24215552 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 25018368 |
|
}, |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 25025536 |
|
} |
|
], |
|
"md5sum": "59cb179392f6b0040b00ee3b874a5838" |
|
}, |
|
{ |
|
"dataPath": "params_shard_81.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3a8854801d6f4a39dfc340b68ff6e125" |
|
}, |
|
{ |
|
"dataPath": "params_shard_82.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f7a8cc4c7bc9f611b3c520bcc851e6a5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_83.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 8486912 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 8494080 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 8503296 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 16760832 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 17793024 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 24215552 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 25018368 |
|
}, |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 25025536 |
|
} |
|
], |
|
"md5sum": "a61e9283bf03c8178d3539e5553b3ca1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_84.bin", |
|
"format": "raw-shard", |
|
"nbytes": 33947648, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
2368 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 33947648, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e4c24e343f51c6ae303c105db9e7eb30" |
|
}, |
|
{ |
|
"dataPath": "params_shard_85.bin", |
|
"format": "raw-shard", |
|
"nbytes": 67895296, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_weight", |
|
"shape": [ |
|
37888, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 67895296, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6b433383533ab3a524aa020230a1e00f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_86.bin", |
|
"format": "raw-shard", |
|
"nbytes": 29268992, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 8486912 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 8494080 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 8503296 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 16760832 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 17793024 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 24215552 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 25018368 |
|
}, |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
592 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 4243456, |
|
"byteOffset": 25025536 |
|
} |
|
], |
|
"md5sum": "3df59a73580d70c779f393007375ac4b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_87.bin", |
|
"format": "raw-shard", |
|
"nbytes": 25018368, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.q_scale", |
|
"shape": [ |
|
37888, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 8486912, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
3584 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 7168, |
|
"byteOffset": 8486912 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.bias", |
|
"shape": [ |
|
4608 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 9216, |
|
"byteOffset": 8494080 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.q_weight", |
|
"shape": [ |
|
4608, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 8257536, |
|
"byteOffset": 8503296 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.q_scale", |
|
"shape": [ |
|
4608, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 1032192, |
|
"byteOffset": 16760832 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_weight", |
|
"shape": [ |
|
3584, |
|
448 |
|
], |
|
"dtype": "uint32", |
|
"format": "f32-to-bf16", |
|
"nbytes": 6422528, |
|
"byteOffset": 17793024 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.q_scale", |
|
"shape": [ |
|
3584, |
|
112 |
|
], |
|
"dtype": "bfloat16", |
|
"format": "raw", |
|
"nbytes": 802816, |
|
"byteOffset": 24215552 |
|
} |
|
], |
|
"md5sum": "d754d22d2eea8cb0fd62aef158fd0669" |
|
} |
|
] |
|
} |