Llama-3.1-Storm-8B-q4f32_1-MLC / ndarray-cache-b16.json
smalinin's picture
Add model files
2b067de
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 5019811840.0,
"BitsPerParam": 5.000895173865207
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 262668288,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
128256,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 262668288,
"byteOffset": 0
}
],
"md5sum": "b78b92f057f4db0b744b7455d0e4bf4c"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 262668288,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
128256,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 262668288,
"byteOffset": 0
}
],
"md5sum": "09a5853fdaf0170a157841ed95038735"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 32833536,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
128256,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 32833536,
"byteOffset": 0
}
],
"md5sum": "16afb839ab8a399260a0a3ee1341667a"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "629cbb25d9448756a2b43d89c517c932"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 32841728,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
128256,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 32833536,
"byteOffset": 0
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 32833536
}
],
"md5sum": "197ec3ad4a2199cd34734a8c4775a7b1"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "339e3c81996845f5f6df641e7c9bc02f"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "268b62cf4d702d95ecbf7095c4ae1f64"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "f58842a4091f04a891ceb82edea60d14"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "686dc8c2e7b05ac6fc2b1c9683afe280"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "8abef2736042d26714295d1869f3fdcf"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "97c511650083d8406081e835d23ff145"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "f756950065ba826ef2f549cf306a1eec"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "b317afe3cb6539a91280ab0ba8966017"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "a48e098663403c5baa1e23ce33d2f04a"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "19135f9a934dfb9fadaa9f9997ee35ca"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "eb4bf80992977b0925ed1978419bb6cd"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "93e736174d08cb12bf8e5c190da26ff5"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "6af7c8fe44a0f636ac6f347d66317c3e"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "66098edde0786c8fe54e94b692be4fd4"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "2150b108096390f8c775e417fc4917e8"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "50854d7895da0e45136367dcd5d6d65c"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "8f597a0f4dd69e6814b01828f6ed936b"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "8339f662dda6738bef77b2b431239ea7"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "7fc347967fcd7ac88ccf72c43075b87f"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3bfb14b88f37e622d512c30cba54b5ec"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "33cd47d01fa13447ac730259c2748776"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "c68203128323172dbfe0aeff78df90b2"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4876c56e8eb88b280f0ff85e4f042f56"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "e78440ca481f64a9429ef63de1a4edba"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "0feb15c229942cf8596832078668dcac"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "6a068770e4da8accbafbd069a0bb6ce0"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3812e21e7ed2fd48e0476c36e6143356"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "ee18a66ae4b195c27c26551900ee74c0"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "b6b43013946dddc148872a93d49dc8ce"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4e2a1bce864232d4d22ee6bacdac238f"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "ae95ac3ddf2a425bcb3d535fb46f1d2d"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "b2d72bd4fcc48903e0421316df58766d"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "c7e5b2ee10c1cf7f633813d8cfa48ca1"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "5a6088e3db0cc0a6ea94abac31741dd6"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "54b80bba0d3122895a0aaf7729edac4d"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "ed57305f482b9cf50a8c206911ddd7f2"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "6a38f5e15aaac6c936d41ad5e1bebb9f"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "2774e83596424bd8444ed24a2eda95bc"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "9bc2f9acd27b6a246fa6c24a7676cb42"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "714c553bd9a51118b2f1ee5776fd807e"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "cd9423183ccc754af43a510ba6ae244a"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "d478be2f28a1db6654e0063e81b2056b"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "bcfb04be0e402e879081f326f81943b9"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "e682d91118726f72c7a55881bcd934eb"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "5042ccb6978ad39ba86c2eec722af730"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "cf03b0f42b9f95ba094600ffe682305e"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "0e1d58c2410d3d05a3fa872b24449a27"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "5b9206dc4ec8842bc10cb6a407e3c5d2"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "9425445d455dd19a71bdf1e4dab1ed5c"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "be10636b659b52e2fdb42d61309cc0a7"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "de1bf52e38cef859c9536a2cd96ebaf0"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "b69d5e76b83da05f1353b02b8b792acc"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "e432214f3dfac521f8634e96fa3b9dbc"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "98f23ac3ad3f625385c9d0eda6bd7e7c"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "5b7208cb350f01adbe192345bee7155e"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "61349731387ea4c22802c01cfb61f239"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "014d2962e706c1a16b9479384785d49b"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "75143943561734aeada5ae875a806fd5"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3a00cc2364a9031b1b217d2162a6cfe6"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "9c7b930c7b5783af54d01b370fc16ed4"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "3462845161e3b10a332186ab89b4616c"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "bfd923c4708d84696be79165ac9bf600"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "6e96117fa194dab01bf768e9e54516cb"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "15c3e5dff5b812493374e3587c64cfab"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "83afc9dd7c4e9483139d91ca63d4e3ac"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "088975ac2d84108a5539e3eb69a97f4e"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "e9824bd7fc3f8f51541cd9ecf220a84c"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "d480b9ee7fd8ec1112aa80bf968446bd"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "2db7f8f049eadc75fa36e0eebcb8bcdf"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "ea0b8c8912393d0af358a9288fba3ffd"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "b94241cc83953b5e7804dac415030992"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3dede810e5b0a4b5c667529900b2ce76"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "4e2af36dc96e42fa4d7a2cc20c51372f"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "980ac3bc4668b8742f266ac831bc9b35"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "00388aae933fbb2ff5946124cd337a4b"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "c9096e8e30ad0e50c1ef4212da047a87"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "0384496bb46b1b0196afe51256d0c12b"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "d4af8edc90f3ec94bc1d7925dcb6f22b"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "c42f4c62852278a3faca2f110efbc2fd"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "4887b41db08c5d7a1a9dfa62aa3100ee"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "b5d360c75fdcd7e997b4b913b9ae50b4"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "072d07629ca3d64f5f1237b90a01553c"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "bd9a45ff1f132504de07fcc9d17582ef"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "58e65e312d8b723f681dcc185be03730"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "50bad7e7fc3305ac1d140a673e764ce7"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "34c8f1a104fb683ff7cee753e5d49910"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "6b78081dea4a0002914c416ed3a2e9da"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "e12a27431c539a1718f63ae9a3f9cbe6"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "59eafb8a8fa0d51e280bef6f931ba287"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "f92beb08d4ad86183b7ef0f21b9a761f"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "efe2a9b65a22994aed626825acf37392"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "266acd8cb53dcf2ad17d8c3012ce8d40"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "dcae74c121eb3112b3ed3d3cde44fa09"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "975f936c649b0fc3dd498979db95c9ca"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "bbdc0f8a45cc788b3399dec54284950e"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "55338f01af8f71c623f65d8b605e3043"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "f4c9a714caed6ecb0132463acbea7a86"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "91df23a03f74c934c17be7ea2d5abe1b"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "a595fd378c03e012663d0a348acecf67"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1378530bd08ebca486e8b750117a3c8b"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "5774804c7e4206e68b6823ab6bad1fb2"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "04dea55da390a4780531e4f2703a412a"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "f439eb6407c750f5f11a0d10be3a9510"
}
]
}