Hugging Face's logo

GrieferPig
/
llama32-8b-sunny

Text Generation
Transformers
PyTorch
Safetensors
English
llama
text-generation-inference
unsloth
trl
conversational
Inference Endpoints
Model card Files Community
llama32-8b-sunny / ndarray-cache.json
GrieferPig's picture
GrieferPig
mlc
00725d9
raw
history blame contribute delete
148 kB
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 4517404672.0,
"BitsPerParam": 4.500381277757404
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 262668288,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
512,
128256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 262668288,
"byteOffset": 0
}
],
"md5sum": "92192c7f50cb11117d9cf2afa17cbd2e"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "3f40f31df9c832a41a72385338aac3f5"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 32841728,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
128,
128256
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 32833536,
"byteOffset": 0
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 32833536
}
],
"md5sum": "43588f001333c201bbb8efa966033e7d"
},
{
"dataPath": "params_shard_3.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": "cfaed1c861535092e163ac0ee4dd5034"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 32833536,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
128256,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 32833536,
"byteOffset": 0
}
],
"md5sum": "6b34f84f2c250bfef16ebcebed38f243"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 33054720,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3686400
},
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 3694592
}
],
"md5sum": "f84c55a10c86aad1979cd934ead58d51"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "c3bd2063d6746e7d9729ef9fa395f504"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "ddecd11b93bdc1a548e3ff3cf8942d62"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "60aad91cdc53ecead31ff5d3258e64fe"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "2363db213b149b5556a87aacf6d0d872"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "b71ec32d4aeea91f9b45ddc8bf52f995"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "eec4a1f8f5edad2904e9bc5ae3011d8a"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "0fae36bf11ef5b2f3fa5f1b2848a9309"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "95f274a8f1da32c1798de11e93212a26"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "75c99103dab46827546bb1d01e61e6b6"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "b5626692798634e330f9c1bb07d00f71"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "59d27be560e3f43645164f000f2d34a7"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "ba05fc260c2542888199573237eae1e0"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "5bc304aae66f775fd01cca3159245530"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "583f5f3f3b792e80e6d804f474a68357"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "e08bbb80010eaccb3715e38a5bbb918f"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "02ad08e3d082d3529ef132dce9dce7c2"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "d714452771bf805c5fe07a5a272093d7"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "d823f421e1089f2f6ace84fc58dde00f"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "e069a871494faabd94b6598aede023db"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "6510055ff6347f542297992f2da42a94"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "f168aa706040e93da49688e475201135"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "c22c03813d7f8eafae109d39f21a2b67"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "95f5827ba323f60bf68fb87e2516a086"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "fefaf712b670599dcef87d45d6b02991"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "8a4355c5f67d6f22fc823a1017082247"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "2429110b4414b39f02b5e1767c91d5b4"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "199cfa9d629330bea7dde64f27744592"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "759c5eb60c90596f19ef5c58af4b6c77"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "12f5c6f65730d3e3d35fccf66c5f3574"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "a474175b9607060c92fb13013967793d"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "54a528133bb4bf74d001164f23c855bf"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "76c75e69c750a0e0707af92664a97f97"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "a2c216f9e5ca2e26c04d0c94075aa4ce"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "4058324e1da3e51761e20848c5e114e1"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "893713daea5f4bf22fb6adaa636cb9d8"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "ef14f9261dd6179e8e92a041b8a24e90"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "b2832c97b63e0ac1a9876e96ca8cd055"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "b4e3f1fa174d7c9c54704db3829f250d"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "b5a1cf842c9cbb47f7dbeb8ea5914ba3"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "cce2742563f1a2a309532100478f3a2a"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "6bd81bcc88b5611f17bb6164765859fb"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "07435fa7e6b8fd0d0710b5bfce882680"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "f3706c1a98f5e9b5036b22c62a951f06"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "a0f315fcdbb9271428bf7eff25e53225"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "c54eb0a0f4e7cee86445c6f1ea38efde"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "e6a142822788b8988de6ae8e2547ecde"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "bb172ed8e85d8eca8bebfa50fc1846f1"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "ae1048444bd4412dcd094396babaa68e"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "675dc3e58ab6020237a125655472e32a"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "da53597ed791cdcb4557b97cfbf62c04"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "85f995014c29c88f414a70292de2afa2"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "693693e802b1785454df206947704017"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "c4d330d24b101efad67bee28053ca6a8"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "5b257a9987ca19326203c8987cdd8fa0"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "8cf37a587ff088c126e692c02b798ce7"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "797a6b3c6020d56d8a278da2bf879141"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "74194c51e613bff30810cf3e6b1c3cdc"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1e94bdf3cf4ec298d0fd1bb920d6a916"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "5ed07a69523752a3177ca0062522a148"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "19c41334ddfa1ca6be93533588fd3b2b"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "d81705ab0eb5ad0c0c6cf12b4f88e8d5"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "871be4b7d65b4c29d6a56516bd7508e2"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "34c6d375c2826d96970c52442d33cadb"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "29c3683004f913686f93b2e9621baa3f"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "9efc311dec2fc4b24e04ca0aca55ce67"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "dd122bb89526e9203721c14b0955a555"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "3b323d39f193c1a2895c76b90c1f5186"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 3686400
}
],
"md5sum": "12242417773f0f61e39323f81a18fab9"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "54ec4094053a2494beb88b20e1b7ce85"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "b4970c7f0d0ff7d5d40f49da69575193"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "ae37fbfc4ec931d585084eb0ac755104"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3715b844613d0500567c4c8c5caf963c"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "1c159c7e3ba9fa7149346f7ac77b33da"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "e0eecbb81c3b0667aeb0a7a839ae9391"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "874931cc5d3589191d799ac6ec59251d"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "7378a91592d673d839df5f0e5c0a7293"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "d93028d2d71093d14955e947c9cc2f8a"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "b595dc23bbde3b0ad6fb137f228871cf"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "45a0c421e372b073f11a78943bf8878a"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "044e94e2cd04a5c9cff2b3334b51a872"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "dc7d09f429c767dce32940c5c10385d1"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3ddd44c88ab6d9a06b77893808623e4c"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "c3fe04669d36d24a0fd4cdcb1f6c59e8"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1ad12f5dbc5875ce0085074577fe120d"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "bfde8fd82bd417379b136d9ec4088611"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "319af07f1bf1fe4eac63ba2921e6b680"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "8e0b932730fb268bf6d5d93b390c56b7"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3ae370be5ce5166b360216911984623f"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "e0dc6a3003dbe4c78263cca01cf24b1d"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "922d2fad4d536dd9230ff1a0b90668c2"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "88605f1273e6eb5acc5297c3cafe1459"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "00ba1f833e417cf36877079dc8d7ab7b"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "3404efaa22dccfabba9ab4771f9cfdf5"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "4dee95a1127ce4b76568ce26b91376c5"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4817b2175422daaea39e9116ae261f69"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "380fb4a83133c22181c1e0d5e98f5558"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
1792,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "3bd72c0322a894c1e2e93acee24f0069"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "e1f95a8b997bb74b707c32bdb259fe13"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
448,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "ff5bccc843d1d086474c6dacb526cadb"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
512,
28672
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "a3b7055d469aa499c76697cee131cff5"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 32505856,
"records": [
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
128,
28672
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
512,
6144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 18350080
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
128,
6144
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 30932992
}
],
"md5sum": "646797718a3bc41d9f11e34d30d91fa3"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 9437184,
"records": [
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
512,
4096
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
128,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
}
],
"md5sum": "41c1d7deb7f1b271b6f1da063b51252f"
}
]
}