| { | |
| "metadata": { | |
| "ParamSize": 507, | |
| "ParamBytes": 5778110464.0, | |
| "BitsPerParam": 4.55004707893633 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 458752000, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_weight", | |
| "shape": [ | |
| 256000, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 458752000, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "581f6c2d88b21fb583e43f7f6028cf67" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 57344000, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_scale", | |
| "shape": [ | |
| 256000, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 57344000, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3613d9463ee55d16ab676080e0a4dcc2" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9d77d9a915af93ce2d2bcf467a187315" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28908544, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 7168 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 25697280 | |
| } | |
| ], | |
| "md5sum": "73dcdd344a7804998745ad6bdf8efbf9" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "449f0b29fcc6fc603469532e08f7867e" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.0.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.0.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "cf946937f65b57651d0cd9dab5a18133" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fcffd48425f63ddd92c316cf73747a84" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.1.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.1.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "75fa2858f084f8d981917bce055531e9" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c8e5f798813da7a1b5d83f544b897bc6" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "7a63c7d93170ea80faeefdfa55facfec" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "82e504b71b9fdf94978a8380bb24aceb" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.10.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.10.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "df82d36cd85a5ee1e4d99995e3e671b9" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9452f6ee26bc5b61ed950e974e45b398" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.11.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.11.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "8a04e974e90f8242f75c3c3ed86ebc88" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2f883cc8a1975e556502768aab8aa1fe" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "dc10740f440de748772d30a2cf7f0e28" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5d78bcc1fad887aae2608801b0ff49f4" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.12.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.12.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "156c0b8f10a699c9aa57149e3140c030" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1e757436832e8e2cff7f6cb31b4d756e" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.13.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.13.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "97fd3b8333b5b7b2f0386e79a09d8de0" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "752138f9c4380234d8aee0664113dd8e" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "0a1754087fde872adf457971555fc1ba" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a8a2bf61429b1c55964ebcdec651a3fd" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.14.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.14.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "130bff917c0fee604112d8161c3639b4" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "796d373866bd97e11bf70408805f028b" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.15.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.15.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "9474827d73a49d623cf8d7959444c8e0" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "351716e6742f2f60dcd9f1b2d7e44b24" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "f2dbda755098afa22a0932852fdd962d" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "940a302682f06a3eeb2ad192b94975d7" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.16.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.16.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "2b1a424d5be78d560ea73183a0c0c915" | |
| }, | |
| { | |
| "dataPath": "params_shard_30.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "62684598adc77ae83375c413c071e42c" | |
| }, | |
| { | |
| "dataPath": "params_shard_31.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.17.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.17.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "bce688b7f9a7a4f3057b96f7c78e0bbe" | |
| }, | |
| { | |
| "dataPath": "params_shard_32.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "42d9afa7f667ff0719310729e240c0df" | |
| }, | |
| { | |
| "dataPath": "params_shard_33.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "e0e02f8b8a2b2b6c2c5db2d050209d9a" | |
| }, | |
| { | |
| "dataPath": "params_shard_34.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "15c42f6eb7fbc21984ad3937d752b59e" | |
| }, | |
| { | |
| "dataPath": "params_shard_35.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.18.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.18.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "4f7a9b8dd4e46fb3666e29bea38d4505" | |
| }, | |
| { | |
| "dataPath": "params_shard_36.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6db73ecaab4ce736f561ede468249296" | |
| }, | |
| { | |
| "dataPath": "params_shard_37.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.19.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.19.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "e6e6b8c064037f9a61784e862bd06f39" | |
| }, | |
| { | |
| "dataPath": "params_shard_38.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "df26370d30899ef3a21931124c739f70" | |
| }, | |
| { | |
| "dataPath": "params_shard_39.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "a32d3675e4bddd406e6ebcdcf613337a" | |
| }, | |
| { | |
| "dataPath": "params_shard_40.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7e4f821db7653ffcb961556a24d3ab0b" | |
| }, | |
| { | |
| "dataPath": "params_shard_41.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.2.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.2.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "dbae62fdd15f2faa77232ea2f4f71b75" | |
| }, | |
| { | |
| "dataPath": "params_shard_42.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "398f5212d8a294819e1f88329da80e96" | |
| }, | |
| { | |
| "dataPath": "params_shard_43.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.20.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.20.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "32983ba180355cfcfe4b7d4250308d31" | |
| }, | |
| { | |
| "dataPath": "params_shard_44.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "56334118d6b3c61e5cfc3e798cd5cc38" | |
| }, | |
| { | |
| "dataPath": "params_shard_45.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "95cfee9bbf3655398a5235d60b3c17fa" | |
| }, | |
| { | |
| "dataPath": "params_shard_46.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0db14be904f016794c2362267293a49f" | |
| }, | |
| { | |
| "dataPath": "params_shard_47.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.21.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.21.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "18764066077c2f3b804f24f7c4357993" | |
| }, | |
| { | |
| "dataPath": "params_shard_48.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1f6a5b382ace19548b43181c4ebbcb35" | |
| }, | |
| { | |
| "dataPath": "params_shard_49.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.22.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.22.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "14843b07637321fcf8438319b411ec98" | |
| }, | |
| { | |
| "dataPath": "params_shard_50.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ad742e5014ff76c424b2bcf5764beffd" | |
| }, | |
| { | |
| "dataPath": "params_shard_51.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "840965c1db059033784a1de6db0a5b8c" | |
| }, | |
| { | |
| "dataPath": "params_shard_52.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0773261fc9fb376fad9ce247d3d7f7aa" | |
| }, | |
| { | |
| "dataPath": "params_shard_53.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.23.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.23.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.24.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "7ba1449744bf4b90d7a8410d951ae3bd" | |
| }, | |
| { | |
| "dataPath": "params_shard_54.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "015c92d1a2259abd9783e9c09fd1948c" | |
| }, | |
| { | |
| "dataPath": "params_shard_55.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.24.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.24.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.24.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "313a7980eb24ce27f4eaff95488bb16c" | |
| }, | |
| { | |
| "dataPath": "params_shard_56.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3daa3e78ba72975f65f1263f58672976" | |
| }, | |
| { | |
| "dataPath": "params_shard_57.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.25.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "f4bbe8b4417dc18fd52a1f901d6903d4" | |
| }, | |
| { | |
| "dataPath": "params_shard_58.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "16297be7b75400c9615262e78bb22e6f" | |
| }, | |
| { | |
| "dataPath": "params_shard_59.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.25.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.25.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.25.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.26.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "4d0064c67970169057bc30df4362865c" | |
| }, | |
| { | |
| "dataPath": "params_shard_60.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "07990ec64ce2cff1fc8802c0145a5533" | |
| }, | |
| { | |
| "dataPath": "params_shard_61.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.26.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.26.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.26.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "a42dfbec720748392bcb28770dcfea5b" | |
| }, | |
| { | |
| "dataPath": "params_shard_62.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e0b346365bb21d2e1c22b8e005ed13db" | |
| }, | |
| { | |
| "dataPath": "params_shard_63.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.27.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "4314d4e919559148ecfcad11309efaf5" | |
| }, | |
| { | |
| "dataPath": "params_shard_64.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cd6223c7f76df633c6702f9298c74973" | |
| }, | |
| { | |
| "dataPath": "params_shard_65.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.27.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.27.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.27.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.28.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "83ef3471267866675b4384645cdc3d86" | |
| }, | |
| { | |
| "dataPath": "params_shard_66.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b40a0a35652eae64df9098fb61170e1d" | |
| }, | |
| { | |
| "dataPath": "params_shard_67.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.28.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.28.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.28.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.28.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "50b896c731508d4db1866392e046b61f" | |
| }, | |
| { | |
| "dataPath": "params_shard_68.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "acaae004e5fcc6b6df8f80d1dd336f75" | |
| }, | |
| { | |
| "dataPath": "params_shard_69.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.29.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.29.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.29.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "4d072a21893238a66098950a428e506b" | |
| }, | |
| { | |
| "dataPath": "params_shard_70.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "68df6a75f06aa4d60c8bb40fc57c15e4" | |
| }, | |
| { | |
| "dataPath": "params_shard_71.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.29.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.29.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.29.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "59378843c469b9f67e5c6838421a6cd4" | |
| }, | |
| { | |
| "dataPath": "params_shard_72.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "dabec2f9f17c3603d22b347dd0d283a2" | |
| }, | |
| { | |
| "dataPath": "params_shard_73.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.3.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.3.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "2afa57068365721551cad660b8749c03" | |
| }, | |
| { | |
| "dataPath": "params_shard_74.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "484491025b3d245bb4d01c8d76319a09" | |
| }, | |
| { | |
| "dataPath": "params_shard_75.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.30.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.30.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.30.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "9799f54e85a2c4d740f7eb6ddd131323" | |
| }, | |
| { | |
| "dataPath": "params_shard_76.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "404bceec731de46fe2931b549381e933" | |
| }, | |
| { | |
| "dataPath": "params_shard_77.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.30.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.30.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.30.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.31.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "604cea7597e6d9620179f10e74ffbb2f" | |
| }, | |
| { | |
| "dataPath": "params_shard_78.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4f0d03da9ffe936a7f27acc9fa85b396" | |
| }, | |
| { | |
| "dataPath": "params_shard_79.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.31.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.31.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.31.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.31.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "2a109d13c58db7ecb60e91f9dd20e77d" | |
| }, | |
| { | |
| "dataPath": "params_shard_80.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.32.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a3760a3254f9d99e159e17bb008e8388" | |
| }, | |
| { | |
| "dataPath": "params_shard_81.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.32.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.32.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.32.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "957cf13ecb76c037a1c3d8511af623c8" | |
| }, | |
| { | |
| "dataPath": "params_shard_82.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.33.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "27bbe2b513b7e96fe7b0d8678d3e5f5c" | |
| }, | |
| { | |
| "dataPath": "params_shard_83.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.32.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.32.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.32.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.32.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.33.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "ef218c747796ec499d8c4879645f19d4" | |
| }, | |
| { | |
| "dataPath": "params_shard_84.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.33.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b00b944813a906f81077e627cd913bc4" | |
| }, | |
| { | |
| "dataPath": "params_shard_85.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.33.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.33.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.33.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.33.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.33.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "61efbbdba707673e7a7c067330a2dd17" | |
| }, | |
| { | |
| "dataPath": "params_shard_86.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.34.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "03395427be7b3b46dbb124428e969c10" | |
| }, | |
| { | |
| "dataPath": "params_shard_87.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.33.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.34.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.34.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.34.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "7c06da46b686cbb6876e213d7a7f279a" | |
| }, | |
| { | |
| "dataPath": "params_shard_88.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.35.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0ecbf386a46750f266662cc1e2793526" | |
| }, | |
| { | |
| "dataPath": "params_shard_89.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.34.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.34.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.34.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.34.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.35.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "c5de48b683a7076390b69697d90cc63a" | |
| }, | |
| { | |
| "dataPath": "params_shard_90.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.35.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c5c86adae657dbe83f910b5159330ec8" | |
| }, | |
| { | |
| "dataPath": "params_shard_91.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.35.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.35.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.35.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.35.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.35.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "71db9d1796bbf1d39fd47364c82e7e78" | |
| }, | |
| { | |
| "dataPath": "params_shard_92.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.36.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "81272fa33ae8e508745977d264ae41ce" | |
| }, | |
| { | |
| "dataPath": "params_shard_93.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.35.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.36.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.36.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.36.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "87223323ad3e69c932233d6376953ca8" | |
| }, | |
| { | |
| "dataPath": "params_shard_94.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.37.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ed0f09bbcd695501a585da62e868781a" | |
| }, | |
| { | |
| "dataPath": "params_shard_95.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.36.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.36.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.36.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.36.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.36.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.36.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.36.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.36.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.37.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "721af0c921f0d507bed441169c377d78" | |
| }, | |
| { | |
| "dataPath": "params_shard_96.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.37.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2557d8e1b348b67827e834ca42d0d22f" | |
| }, | |
| { | |
| "dataPath": "params_shard_97.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.37.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.37.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.37.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.37.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.37.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.37.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.37.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.37.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "70dc7a4b3180f0db9f3eb707b8a30b6e" | |
| }, | |
| { | |
| "dataPath": "params_shard_98.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.38.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bbca11ea40ec53c7221ccb5a9f3250db" | |
| }, | |
| { | |
| "dataPath": "params_shard_99.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.37.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.38.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.38.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.38.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "cd0a898a4a35eafa30f69d8c55666ec7" | |
| }, | |
| { | |
| "dataPath": "params_shard_100.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.39.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b5006c14282c975cc6ef1f66507a4d19" | |
| }, | |
| { | |
| "dataPath": "params_shard_101.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.38.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.38.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.38.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.38.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.38.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.38.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.38.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.38.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.39.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "08ecdc8b63a8035706a12b1fbc77664e" | |
| }, | |
| { | |
| "dataPath": "params_shard_102.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.39.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "957f24bf32d360ace5cfb9f51b1451fe" | |
| }, | |
| { | |
| "dataPath": "params_shard_103.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.39.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.39.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.39.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.39.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.39.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.39.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.39.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.39.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "4f7c461d90072999ea9cf11aab8a38cb" | |
| }, | |
| { | |
| "dataPath": "params_shard_104.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "23e270e726b907aa91c4e3c065acd39a" | |
| }, | |
| { | |
| "dataPath": "params_shard_105.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.39.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "3e3ac8b52e514fbadfd8db34847aa798" | |
| }, | |
| { | |
| "dataPath": "params_shard_106.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.40.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8049d10a234bd075e6608253d177c5ee" | |
| }, | |
| { | |
| "dataPath": "params_shard_107.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.4.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.4.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.40.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "f0db144e8417ec10ef3f68c38a3dbd34" | |
| }, | |
| { | |
| "dataPath": "params_shard_108.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.40.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b1f9ecfbcbb486dc5007ca4710d05f79" | |
| }, | |
| { | |
| "dataPath": "params_shard_109.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.40.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.40.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.40.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.40.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.40.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.40.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.40.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.40.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "07c1b40bc7d57b818d0e2959355e03f5" | |
| }, | |
| { | |
| "dataPath": "params_shard_110.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.41.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4e755b65a605d4f8bfada7e00fdd2178" | |
| }, | |
| { | |
| "dataPath": "params_shard_111.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.40.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.41.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.41.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.41.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "baedaa05248279d2fc4db2dcfa9b7971" | |
| }, | |
| { | |
| "dataPath": "params_shard_112.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4f6af57921dfb47d821f37aef5c28669" | |
| }, | |
| { | |
| "dataPath": "params_shard_113.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.41.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.41.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.41.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.41.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.41.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.41.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.41.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.41.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "98e4865123ebe1b769035e8603a1cb3e" | |
| }, | |
| { | |
| "dataPath": "params_shard_114.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5c57d68b2981bc7abfc7b1bca436f2f1" | |
| }, | |
| { | |
| "dataPath": "params_shard_115.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.5.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.5.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "1fb6240d7330e2d89bd7cd9602982dc4" | |
| }, | |
| { | |
| "dataPath": "params_shard_116.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "85d9a33e8b538615f0919d970159cab2" | |
| }, | |
| { | |
| "dataPath": "params_shard_117.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "e061ada5689bfc093a72c9a51498e734" | |
| }, | |
| { | |
| "dataPath": "params_shard_118.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1a270e7a25e7546ad9c92d36258652ae" | |
| }, | |
| { | |
| "dataPath": "params_shard_119.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.6.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.6.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "53c0fb2f79bad56cc0d4d5988bcb21a5" | |
| }, | |
| { | |
| "dataPath": "params_shard_120.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8efb466707284864f76911509f7f8557" | |
| }, | |
| { | |
| "dataPath": "params_shard_121.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.7.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.7.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "e1599620555fc631a40f8305336206d7" | |
| }, | |
| { | |
| "dataPath": "params_shard_122.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5bd7cfc1c4a7f3cc30dd2595a741f875" | |
| }, | |
| { | |
| "dataPath": "params_shard_123.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826048, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 924672 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 26614784 | |
| } | |
| ], | |
| "md5sum": "def4f59751241a114b2eced52edff5b1" | |
| }, | |
| { | |
| "dataPath": "params_shard_124.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25690112, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 1792 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 25690112, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d8c30599ef73a51613cc2c41394399ec" | |
| }, | |
| { | |
| "dataPath": "params_shard_125.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31223808, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.8.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6429696 | |
| }, | |
| { | |
| "name": "model.layers.8.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 6436864 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 6444032 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 21124096 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 22959104 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 30299136 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 31216640 | |
| } | |
| ], | |
| "md5sum": "3684830f59f6755905f843adcc696789" | |
| }, | |
| { | |
| "dataPath": "params_shard_126.bin", | |
| "format": "raw-shard", | |
| "nbytes": 51380224, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 51380224, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7f028d14ee44583e6d8a160c58a6f422" | |
| }, | |
| { | |
| "dataPath": "params_shard_127.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33510400, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 3211264, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 6422528, | |
| "byteOffset": 3211264 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9633792 | |
| }, | |
| { | |
| "name": "model.layers.9.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9640960 | |
| }, | |
| { | |
| "name": "model.layers.9.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 9648128 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 8192, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14680064, | |
| "byteOffset": 9655296 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 8192, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1835008, | |
| "byteOffset": 24335360 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 512 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 7340032, | |
| "byteOffset": 26170368 | |
| } | |
| ], | |
| "md5sum": "22b66d4a54d6fcdc6c67c49376f3bc31" | |
| }, | |
| { | |
| "dataPath": "params_shard_128.bin", | |
| "format": "raw-shard", | |
| "nbytes": 924672, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 128 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 917504, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 917504 | |
| } | |
| ], | |
| "md5sum": "3b5e874513a64b93d2437c958569ec45" | |
| } | |
| ] | |
| } |