Hugging Face's logo

numen-tech
/
Hermes-3-Llama-3.1-8B-w4a16g128asym

Text Generation
MLC-LLM
English
Llama-3
instruct
finetune
chatml
gpt4
synthetic data
distillation
function calling
json mode
axolotl
roleplaying
chat
conversational
4-bit precision
Model card Files Community
Hermes-3-Llama-3.1-8B-w4a16g128asym / ndarray-cache.json
numen-tech's picture
numen-tech
Add weights
e4a6264
raw
history blame contribute delete
146 kB
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 4140998656.0,
"BitsPerParam": 4.070120983102826
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 262668288,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
128256,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 262668288,
"byteOffset": 0
}
],
"md5sum": "3b80c5597ef787959f5efe105675e1fc"
},
{
"dataPath": "params_shard_1.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": "623d3ef1f630c8cdb8618a5d5ddf7762"
},
{
"dataPath": "params_shard_2.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": "13d42155239cdecfadf0c5659be0affe"
},
{
"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": "5e9a427ab3cc94d7b9befb2bb34d747d"
},
{
"dataPath": "params_shard_4.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": "5f7f10736b8456eb2e5669abd113c94b"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "54db44293054b74bc44a0537ddceab21"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 21962752,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
128256,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8208384,
"byteOffset": 0
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8208384
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 8216576
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 9134080
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 10969088
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 10977280
},
{
"name": "model.embed_tokens.q_scale",
"shape": [
128256,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8208384,
"byteOffset": 10985472
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 19193856
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 19202048
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 20119552
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21954560
}
],
"md5sum": "85994ff252594013aaffd967ce5f8c01"
},
{
"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": "5d28587cad87cbfc0fd2d6f2f5d90f7d"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "330ccca10cc191971834100753236358"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "4ef54e5fbd8327d0ad95fab7d94301e5"
},
{
"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": "291217403fd4f75014517ba71bb21242"
},
{
"dataPath": "params_shard_11.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": "a788939ba9ceb121f340764102302511"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "0704aed50fe7a8fbb6db9be0c7da7ac6"
},
{
"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": "312caf2185be0ae48c3a929b3cf6b0eb"
},
{
"dataPath": "params_shard_14.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": "883359dadec88ba8fbfff0c685da7086"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "1079783c8d49f4a89d7744f7099d7c29"
},
{
"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": "a7d5afc31dc22faf0cde391c690f77da"
},
{
"dataPath": "params_shard_17.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": "0e8ada0310ebdb3cacb9c18a1e9541ca"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "4a1bc3f9e95a1fd4c22870bc4dec64a6"
},
{
"dataPath": "params_shard_19.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": "3928ecb54b5054440899b1664b56cbca"
},
{
"dataPath": "params_shard_20.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": "7b42b7b38b7ab8c450e14ed63529f144"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "a9e57186630e9135fb49fd0fb3251e43"
},
{
"dataPath": "params_shard_22.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": "a09d70aec3aa95be274cc04ba49bd84c"
},
{
"dataPath": "params_shard_23.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": "a40f5f4c2d0b82633c894e968a814451"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "a33e1491d5289c95ba153a029ebdb111"
},
{
"dataPath": "params_shard_25.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": "82104b1a68cdfed6684e827435aac1f1"
},
{
"dataPath": "params_shard_26.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": "d3e687721edfc9783f25aec444002c95"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "e63a179a997ff2e2664bd854c663aebb"
},
{
"dataPath": "params_shard_28.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": "2838cf88e2512f7f89bc1db6bce34472"
},
{
"dataPath": "params_shard_29.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": "66519cb3c6d6bda00c9aea633601083f"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 24379392,
"records": [
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21626880
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22544384
}
],
"md5sum": "dc472578db13a425f897a2519955ebcc"
},
{
"dataPath": "params_shard_31.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": "0a33a52e8f7dfb0afd50c2dab96e41db"
},
{
"dataPath": "params_shard_32.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": "5c611ee75070226db7194079e467d560"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "fd8f0b8dfa9d45692929160715c9dcdf"
},
{
"dataPath": "params_shard_34.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": "43731dfde25b7479b2be6fd7cf5d54a3"
},
{
"dataPath": "params_shard_35.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": "2f58e60915faffe9f8e1699c7211b8c6"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "9df9ce2a50f605e1b008d65fbc310000"
},
{
"dataPath": "params_shard_37.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": "fcb149cdc6a4fce508c40592c711c8df"
},
{
"dataPath": "params_shard_38.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": "89f789946479f17e5c5863b3838a1420"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "5600a64fd70e3d8f1779855e2bbbcf59"
},
{
"dataPath": "params_shard_40.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": "2c8ff179a0b26a08b64a37cd98b28091"
},
{
"dataPath": "params_shard_41.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": "02c937105dede46ae31636ba89b834bc"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "70e1f1e3236714607039bdeaf1c4daf2"
},
{
"dataPath": "params_shard_43.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": "9e18591e4000f419d46ba10f47dfd828"
},
{
"dataPath": "params_shard_44.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": "b8a57909f06e631aff7bc372037edc00"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "328e79d88624b23784efabdcd7f79670"
},
{
"dataPath": "params_shard_46.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": "f9995bcb3045ce1821dcd0879b182f1f"
},
{
"dataPath": "params_shard_47.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": "a21c1c047b421e69d281fa245f701b95"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "1ec48b4a5302e1aa8ff8106dfc3559b3"
},
{
"dataPath": "params_shard_49.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": "475ed2ef139c6bd568b9d7a3c841cb73"
},
{
"dataPath": "params_shard_50.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": "fbb857e6d9808f57f2a94b1d88224a61"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "861a9868420adf31a6798242d3f76169"
},
{
"dataPath": "params_shard_52.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": "9deaedbd1b27f66e335fed5843b6a30a"
},
{
"dataPath": "params_shard_53.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": "97cd897246c807625985005c84306382"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "79569f0c36e35adf21600dd6a8bd576f"
},
{
"dataPath": "params_shard_55.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": "4f1099ad7bf863dcfb847fb7d7c86112"
},
{
"dataPath": "params_shard_56.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": "581d3b11ffa0c2d15854161f6f6302e4"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "7b354309dfad2cae6cd6ae85d088c7d5"
},
{
"dataPath": "params_shard_58.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": "0958e4c7debb0b05be366c2e3af556e7"
},
{
"dataPath": "params_shard_59.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": "caf946cd7991aa9b19991fb4a68c88dc"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "4bcb0252f920c5d0b5f2a1bd1564ad64"
},
{
"dataPath": "params_shard_61.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": "03b65391b91979bb7863980c009ccab6"
},
{
"dataPath": "params_shard_62.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": "df334aa9fff26c6f8d3deadee3b1f360"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 24412160,
"records": [
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21635072
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21643264
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21651456
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22568960
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24403968
}
],
"md5sum": "9d9ed790d17b0361bfcc8b772540c7f9"
},
{
"dataPath": "params_shard_64.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": "eeff29ec2b0e013c53e1d699333a51cd"
},
{
"dataPath": "params_shard_65.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": "251f5378a30eb6d19e15d9ada7e11713"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "599d5a1d9cd75eb54b3dce429886d5dc"
},
{
"dataPath": "params_shard_67.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": "341d39b1936798cb64e1c7af29a7182f"
},
{
"dataPath": "params_shard_68.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": "4c5e493e82e9224d863f14731886124c"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "abca13883a3cd16b15d32f6d582cb4e6"
},
{
"dataPath": "params_shard_70.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": "60708231755750bcf941bfc9927a142b"
},
{
"dataPath": "params_shard_71.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": "e8cc0f6555e82aa71bcc850793e29495"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "f39632b98679fe7a7456211538466529"
},
{
"dataPath": "params_shard_73.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": "345066207c28fe28ac74af42e1df6884"
},
{
"dataPath": "params_shard_74.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": "46f62c0d85c6a9191e1dcb4e8de2379e"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "eb03120e31fb29092936a66f206aa716"
},
{
"dataPath": "params_shard_76.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": "9dee39b48ce67028f5e30fc1c0b78be9"
},
{
"dataPath": "params_shard_77.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": "cb8411326cfccb16302030590830ab34"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "c6e9041f0f9ecf5186ae9cebbd0eacc5"
},
{
"dataPath": "params_shard_79.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": "b8c43e70b8c6f8487241d462f8997344"
},
{
"dataPath": "params_shard_80.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": "956daba8d96a12c6579fdc36ddf430a0"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "25b122c7cfb471534343fc28324f74b3"
},
{
"dataPath": "params_shard_82.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": "dbef49628f2585032e33d549cfc9d4c6"
},
{
"dataPath": "params_shard_83.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": "03868532d65389f31e135c1c7b59b04e"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "b092495a1abb24693b2b2c156d6ea88f"
},
{
"dataPath": "params_shard_85.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": "88c2ef84cf44471e5a3fb6e5e2936a03"
},
{
"dataPath": "params_shard_86.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": "2c5ec9918f28a962fa99147b1a204617"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "5170cead5dda5b0b4d34b2eea2e0a163"
},
{
"dataPath": "params_shard_88.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": "d05e6e2c93a5fd9e530bc52e0c221025"
},
{
"dataPath": "params_shard_89.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": "3c8219af4fb63782f47c6160b89c87b8"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "271e8d5070f9ee29fa495c87982acda9"
},
{
"dataPath": "params_shard_91.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": "c6f5111f465d7bcef27e1eb0da897a80"
},
{
"dataPath": "params_shard_92.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": "ec00dc82c0174fe2b64edb7569e2f73d"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "809e4ceb25adc4a3e38e18fd34f20b8d"
},
{
"dataPath": "params_shard_94.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": "c407eb190ef5704f350fb07631ab12bf"
},
{
"dataPath": "params_shard_95.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": "9ddf2b37afb4c4326502bd1e634fc6fc"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 24395776,
"records": [
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "3e893d429cf4e100d8d978301b0f3fae"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 21626880,
"records": [
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
}
],
"md5sum": "d9d940dcb1c0a47c21ca86c28e9079da"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 21626880,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 12582912
},
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 12976128
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 21364736
}
],
"md5sum": "ecebad5bba01ab8345b91fc4020d825c"
}
]
}