Hugging Face's logo

mlc-ai
/
DeepSeek-R1-Distill-Llama-8B-q4f16_1-MLC

MLC-LLM
web-llm
Model card Files Community
DeepSeek-R1-Distill-Llama-8B-q4f16_1-MLC / ndarray-cache.json
riczhou's picture
riczhou
Upload folder using huggingface_hub
196c6f3 verified
raw
history blame
148 kB
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 4517404672.0,
"BitsPerParam": 4.500381277757404
},
"records": [
{
"dataPath": "params_shard_0.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": "90455a89d1f126d08436b3f9763bfd45"
},
{
"dataPath": "params_shard_1.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": "e6b4a4d9bea78df69d0088aa994566eb"
},
{
"dataPath": "params_shard_2.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": "75c27a106939535bb413ce004e292087"
},
{
"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": "ce2b00d836f32fd6700a2fa645ac7fa4"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "29bc2209724cbf206493b5f76180cb01"
},
{
"dataPath": "params_shard_5.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": "196b42d163f5f1283125589a356f2073"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 27279360,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 3686400
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 16269312
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 17842176
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 26230784
}
],
"md5sum": "437d8469f74ab0147bc68a6ed36814c0"
},
{
"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": "db6351591ae51d4b5bcaf7c97593e165"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 25182208,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7340032
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11018240
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11026432
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23609344
}
],
"md5sum": "77081220fd58e41336658371f58c3c95"
},
{
"dataPath": "params_shard_9.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": "3106bdda26a5cf8e7a05e1503c34d1b2"
},
{
"dataPath": "params_shard_10.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": "32603b1f7fd78eeadb18c94b8a8ca3b7"
},
{
"dataPath": "params_shard_11.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": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 9437184
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16777216
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20447232
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "cab7424429ba55957f7377b72541c00b"
},
{
"dataPath": "params_shard_12.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": "895e90a5570452302b031694f41dbbdc"
},
{
"dataPath": "params_shard_13.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": "5c04679846af203f2fabc49b0f44a689"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 18350080
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22020096
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "23ca003c8b433892387e37dfc489f422"
},
{
"dataPath": "params_shard_15.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": "bb96fc90f26c6630643e79669e9bb6c4"
},
{
"dataPath": "params_shard_16.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": "159494a73a6367bcb8da5ea639203614"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 30932992,
"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": "float16",
"format": "f32-to-bf16",
"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": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "6399debb7bfa72c5f37385fee75b7746"
},
{
"dataPath": "params_shard_18.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": "b8ad6cdeff1abbd5d9c708b800ba74c3"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 27279360,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 3686400
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 16269312
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 17842176
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 26230784
}
],
"md5sum": "a696c5920ba15c74bf751a20bafee4d9"
},
{
"dataPath": "params_shard_20.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": "dc437477abad01a92e63e063757e70d6"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 25182208,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7340032
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11018240
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11026432
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23609344
}
],
"md5sum": "6f8ee50d57c1f57ddfd8e6fd33575c2e"
},
{
"dataPath": "params_shard_22.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": "8bd76cb3842307aceab2c3d0ba1942cc"
},
{
"dataPath": "params_shard_23.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": "4fdcf693a0eac4f7139c0d4c8863cc1c"
},
{
"dataPath": "params_shard_24.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": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 9437184
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16777216
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20447232
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"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": "ce575293c246b71dce90abda47915912"
},
{
"dataPath": "params_shard_25.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": "75cc2f0866d4a399a1710251eae099fa"
},
{
"dataPath": "params_shard_26.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": "023829720f0545c9a5d29297165b028e"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"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": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 18350080
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22020096
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "cf5c894ca643aafbb2b749c90dbd992a"
},
{
"dataPath": "params_shard_28.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": "5ed8ecb07f1d1482eeeb52a832a0e866"
},
{
"dataPath": "params_shard_29.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": "b488bad0bb9c2ee38b29e1074b4971fe"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 30932992,
"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": "float16",
"format": "f32-to-bf16",
"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": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "a405ed63f8a50dfb47a0f6ad0c565fc2"
},
{
"dataPath": "params_shard_31.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": "0de8617e0621dd325e565598ed0a2b79"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 27279360,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 3686400
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 16269312
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 17842176
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 26230784
}
],
"md5sum": "8591c5bec40ef15979db84e7b3deb2fc"
},
{
"dataPath": "params_shard_33.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": "6b81dd18dccc51a6bbc026530fdb8d42"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 25182208,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7340032
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11018240
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11026432
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23609344
}
],
"md5sum": "df064fed33251fdbe07304db5e39998b"
},
{
"dataPath": "params_shard_35.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": "8612c16a021ff57b77bea9d98b74cb53"
},
{
"dataPath": "params_shard_36.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": "e66b071242acf3a61b8ed654326704ae"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 9437184
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16777216
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20447232
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "a6900cdfbbe6923e97f51884c730a071"
},
{
"dataPath": "params_shard_38.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": "6002dc71db33c07bf686fa57b760194f"
},
{
"dataPath": "params_shard_39.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": "5c0876577139af9a70a44ffcbc422806"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 18350080
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22020096
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "7951e0149d0e0c202c6e8c77f103bfd6"
},
{
"dataPath": "params_shard_41.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": "3cb9a5c03b56092f8858737748d842bf"
},
{
"dataPath": "params_shard_42.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": "cbe0f4488aa2b2f0586891510cfe9ccc"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "386e677acd4023bbb16b5f2bd6e4da96"
},
{
"dataPath": "params_shard_44.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": "d006075824d4c81af21b752c690ba9f6"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 27279360,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 3686400
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 16269312
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 17842176
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 26230784
}
],
"md5sum": "0ad7238273d267734f12c16fd0874cf5"
},
{
"dataPath": "params_shard_46.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": "4454b6dbade2920e226c7d58e492c385"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 25182208,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7340032
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11018240
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11026432
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23609344
}
],
"md5sum": "35ab0453a16b526a34764b59f6d4da9c"
},
{
"dataPath": "params_shard_48.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": "39212b2e7af56b50762d5533df333e88"
},
{
"dataPath": "params_shard_49.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": "36d9f2b06c115b4228a0af111ff0e94e"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 9437184
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16777216
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20447232
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "3bca388aebf970b8032985980eb53cda"
},
{
"dataPath": "params_shard_51.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": "d6038156dbe786430d81950dd0f96a78"
},
{
"dataPath": "params_shard_52.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": "374d96d8edf39d36128b8aef80f911c4"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 18350080
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22020096
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "3804896676a5ad9072f188e60394b214"
},
{
"dataPath": "params_shard_54.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": "5d8025e8926719db4f178fe78e9e60b2"
},
{
"dataPath": "params_shard_55.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": "bbb2ed8b3f6ba751968ef66047601858"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "18a475adc4f8fcc7e162eae179ead5b7"
},
{
"dataPath": "params_shard_57.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": "ece93bac9742b2ab0af83bc4fc46701c"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 27279360,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 3686400
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 16269312
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 17842176
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 26230784
}
],
"md5sum": "1a2c0bb8eb316f75d84e9840f7e760ae"
},
{
"dataPath": "params_shard_59.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": "b05dac3098f062b6bdef332166d4a50d"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 25182208,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7340032
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11018240
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11026432
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23609344
}
],
"md5sum": "03239f0a72530f423c51cfa8e9275fa6"
},
{
"dataPath": "params_shard_61.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": "03272ba0c23383af99c3b47da6d7ad08"
},
{
"dataPath": "params_shard_62.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": "4c9278b66f69a65e2b0134a322947221"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 9437184
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16777216
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20447232
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "327a6e459043cac033da394dab257a27"
},
{
"dataPath": "params_shard_64.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": "96b43c7b8e1204e924510ca5d5640174"
},
{
"dataPath": "params_shard_65.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": "7e86a802866030c956d28025dee64c6b"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 18350080
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22020096
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "12b61122a272136f5bbf92b19f3e39e8"
},
{
"dataPath": "params_shard_67.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": "95e407450d9703ef088d76f882dce8f6"
},
{
"dataPath": "params_shard_68.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": "21f3ca030d9f058a4b262f4a907ac67d"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "2de0e951e61af4105a6e2c11678fc57b"
},
{
"dataPath": "params_shard_70.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": "d18c92782dcf0953f842331747c0f199"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 27279360,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 3686400
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 16269312
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 17842176
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 26230784
}
],
"md5sum": "2ee4312fc3c067f588be262439abf91b"
},
{
"dataPath": "params_shard_72.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": "07971fad4d67015b938041ce2f42983f"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 25182208,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7340032
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11018240
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11026432
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23609344
}
],
"md5sum": "72c03054d92fac4acb86ae256578d7fc"
},
{
"dataPath": "params_shard_74.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": "6c7310f30e42153b0f816804795275f9"
},
{
"dataPath": "params_shard_75.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": "c2785d51258ec25da7dee538004228e1"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 9437184
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16777216
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20447232
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "cb9d06b60a51d4eec9d35fd7e45d115a"
},
{
"dataPath": "params_shard_77.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": "6b82e35ff10c45958f9aa260a3831d13"
},
{
"dataPath": "params_shard_78.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": "aa381f93d4e8d9f41cfca49e9cc4df7d"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 18350080
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22020096
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "9e67647b021528ce442379f83fd63575"
},
{
"dataPath": "params_shard_80.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": "17d935a5a59c124afb3c23ec226780f3"
},
{
"dataPath": "params_shard_81.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": "3c186103c9e63ba86916971c7cee4772"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "dee81cfb73f4065bc9186968514be2a2"
},
{
"dataPath": "params_shard_83.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": "99fe6ba1e050ff74d528da92b4d7e2bc"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 27279360,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 3686400
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 16269312
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 17842176
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 26230784
}
],
"md5sum": "1d8084ccad662d56e12f29230e466a60"
},
{
"dataPath": "params_shard_85.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": "03cd5c98472931b0f434c9f6ff678747"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 25182208,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7340032
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11018240
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11026432
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23609344
}
],
"md5sum": "469ac6d1d4b7aec85cbe90431ade551f"
},
{
"dataPath": "params_shard_87.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": "5e8849cf40f49cf0eefc64c4701ccf51"
},
{
"dataPath": "params_shard_88.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": "6ca89b103dfa47489b12b821aac87c74"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 9437184
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16777216
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20447232
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "0ecbca2cad7cbcc004f9c293486e5f1a"
},
{
"dataPath": "params_shard_90.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": "24b3d4932f01c837ab924b5026814b79"
},
{
"dataPath": "params_shard_91.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": "619a3fc14a8ec7fdb7bfe33cf334fb1e"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 18350080
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22020096
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "154ef8c1bc577bf4743374052ba54738"
},
{
"dataPath": "params_shard_93.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": "d84fe2cd5020fa8b58b87f811f765987"
},
{
"dataPath": "params_shard_94.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": "be2f3624b95f358d12d4e4737aa8b98b"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "0ea7d27a7fe7db024db8156b2c4f33e4"
},
{
"dataPath": "params_shard_96.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": "43c3b27ecff7f60ae9b7b9839e243250"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 27279360,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3670016
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3678208
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 3686400
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 16269312
},
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 17842176
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 26230784
}
],
"md5sum": "66bab4be1656b8624c44f63d016e7846"
},
{
"dataPath": "params_shard_98.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": "1355eb4837e80d704ef7852a4dfa4e60"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 25182208,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7340032
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11018240
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11026432
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23609344
}
],
"md5sum": "ba1fb5869a9726583698397cde46d55e"
},
{
"dataPath": "params_shard_100.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": "75e0e3a7c979b217efcd32bd20ad5662"
},
{
"dataPath": "params_shard_101.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": "2cf1300f1bddbc3cedacbb036d9d9faa"
},
{
"dataPath": "params_shard_102.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": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 9437184
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16777216
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20447232
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"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": "e3decc41540b2a25305c6f4518dea2d0"
},
{
"dataPath": "params_shard_103.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": "0879c3eab16329c368cbb51a8a922146"
},
{
"dataPath": "params_shard_104.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": "cd4ce18825600be67b5eef555fe84501"
},
{
"dataPath": "params_shard_105.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": "6319b5906b36a200a67e2a99678185e0"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 32833536,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
128256,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 32833536,
"byteOffset": 0
}
],
"md5sum": "51becee22d4a53fb23483900cf2507ae"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 22044672,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"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": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11010048
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 18350080
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22020096
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22036480
}
],
"md5sum": "8536c576e3e6bcc1022286fa972b27ed"
}
]
}