Hugging Face's logo

numen-tech
/
Meta-Llama-3.1-8B-Instruct-w4a16g128asym

Model card Files Community
3
Meta-Llama-3.1-8B-Instruct-w4a16g128asym / ndarray-cache.json
numen-tech's picture
numen-tech
Add weights
1714933
raw
history blame
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": "fd8932dc80b7916f9b6fddb6182131d0"
},
{
"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": "9c83c5ccdd0ba8e2b9256f2968ee08d1"
},
{
"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": "d1f365499d190f123c79dbd90e90e920"
},
{
"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": "6f8a9aebda7f1e4ae24c52a4831ee04c"
},
{
"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": "025f1be2710a8c96ba7e6c33701d0834"
},
{
"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": "0a51d4de2d2ee642d2061bab2423166e"
},
{
"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": "b583780a6b0777028c3365b36a0ba9dc"
},
{
"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": "7aa58d10d849a4c78171acd596be462e"
},
{
"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": "f1a8bda12156b138eddb8983362ccccc"
},
{
"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": "a7aa4d084c42b5a1875444ae02c649b8"
},
{
"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": "032823e0fe8cda4fd31a8479bc677430"
},
{
"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": "fd1ff619e2828f8f3d8285e6e6bf638e"
},
{
"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": "8b5fd625c560307343df185dd261abdd"
},
{
"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": "6085d480f2e402717eaec4afad2e5d77"
},
{
"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": "ca432c21f9b1f7a5578f5eb19d57ce07"
},
{
"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": "f667dda149870f7fd1f147b395ae5b7f"
},
{
"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": "d0556d6fc93cfa0696fb111bce975666"
},
{
"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": "6f97e0c92e93885ab15e4e276d762cdd"
},
{
"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": "23e98181f485c6bd54a0557a7c665239"
},
{
"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": "8c058211cb123da97794ed18537830e9"
},
{
"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": "c943c0b837102eb77f67e190ddd89fe8"
},
{
"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": "2d9e252274acd7618bd744a922a65adb"
},
{
"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": "19dc12c3e660ee84b0f83f057a70e51e"
},
{
"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": "a8f0344a4a945caeff95c3332fec422a"
},
{
"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": "df5d06b3aae3d4f35382b6065a9831ef"
},
{
"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": "6adee8f031bce4cd64d423d755526451"
},
{
"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": "7fe3d6e7acbaf24ec59e1ba8db22eff6"
},
{
"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": "1b7111730a5ad630963f31c40c5cbc1f"
},
{
"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": "98b15795df6e3061f04c833e007a27cf"
},
{
"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": "f83854ed351e27a4f16ae34b158142bd"
},
{
"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": "5fe7f27c4f2b0b188035ee65fd9a7e40"
},
{
"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": "03cb5f30e5cbf1b50c3f318fb1176993"
},
{
"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": "4d491bf90716531d0422de22b3e4c22f"
},
{
"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": "6aadd71eb6869ff2e1bf92f3d9084814"
},
{
"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": "ac34aafa5409e61a1e60be7742474253"
},
{
"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": "484d8fcaf66cbdd7abc32a7f728fbfd3"
},
{
"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": "6ba4611854ba3421e80d67686b2d9ed2"
},
{
"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": "913caf8d08c70e93a61b5bb892f375e8"
},
{
"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": "78b14be9c87042342c0b5d405983f1e4"
},
{
"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": "fd0293e0c3756fe8f336ec629c4bd8c8"
},
{
"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": "48224a078bc28d248984d153b9e642a6"
},
{
"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": "a7245706432d23518b32166c5bcab28d"
},
{
"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": "f772a48f874a0a0d7bef059302cb6bfb"
},
{
"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": "8da7c1a527fe4655cea4d1a9e7c90f5b"
},
{
"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": "9360ba89f4188bb25445f7e61ad4de23"
},
{
"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": "347e548c53deb3ea4c64bb23e5cc0982"
},
{
"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": "ecf41b334b916b1c2cb18ca276fceb7f"
},
{
"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": "344b7c4e2269bb4f655d1bb9e6e335b2"
},
{
"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": "c54db7ee049a7ddf6b7fa38917691bcd"
},
{
"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": "1795dc9a88d83b4b8e294c91a5b8c439"
},
{
"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": "c9e06464606ca102354dbbff45af1dd6"
},
{
"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": "9c9ae15c6664633afd11a926be494b57"
},
{
"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": "fbf76020a0147f81f9644d33d090d8ab"
},
{
"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": "b6534ee4a38ab40fb8503024047b5267"
},
{
"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": "2ca4f8f609653952aa846ed69ee30133"
},
{
"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": "501f4aa92607ee27813aeac20b868cf9"
},
{
"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": "5f8467a171b4296adb1ec3124c07cb6c"
},
{
"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": "cbeb06e9ddb1b93d8be3965718b0a74f"
},
{
"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": "671011219978ef5ed4a7b99445b7d81e"
},
{
"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": "3d36b9297ef4969ca4fe622a17a72d40"
},
{
"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": "8933ffd7f535ad5d2792b324dd790443"
},
{
"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": "dc44f393e0a0d3e137a762882d4f6e11"
},
{
"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": "b92af8d981de097ff533f3ea9c61c974"
},
{
"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": "16b3b80ce6ef4b104fa4aae2ab78fb8b"
},
{
"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": "9d0c942001282b8c9d3634917d8f7943"
},
{
"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": "f23d38411a629da664cda0a64f94fb49"
},
{
"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": "c503ce0311dd66ef44072f17836ffd64"
},
{
"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": "5a7fd388a7d5de146cf1a37331a30408"
},
{
"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": "cae6ca0328d16b5102f78169f5bb11de"
},
{
"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": "ece46718aeb74050dcf35c536067ae6c"
},
{
"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": "408d8be10d377ecd969dd4ec6b23f2f3"
},
{
"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": "19a92b2d754909677b1aa0d05e6a6d2f"
},
{
"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": "268df67e2010ce8e10b640402b988b74"
},
{
"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": "2c35b02f427966ffdc06214ce48f6d39"
},
{
"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": "b7623b3b169dc1b9a3fb8734da3196b8"
},
{
"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": "b349df5d242457aadbe17733e1d79625"
},
{
"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": "3bf2e2a099df96de52dab509fd453dd4"
},
{
"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": "6a8d5ba8cb58623e26ff0b13d581630e"
},
{
"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": "c3f0d6c6f220b6e09406dbf944623ab6"
},
{
"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": "d42f2f3ac84889e19a7fc9d3f9fd66db"
},
{
"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": "dffc34310de37e5da2869c14b0e63373"
},
{
"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": "7336e55a03f7f3a1e2ec9294e9a5d6ec"
},
{
"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": "d5731b5e958b588bbf33891da553eb93"
},
{
"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": "e3c38eb46d0e258b517ad4e2dbb275c6"
},
{
"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": "1d1fa546c3312f3c8edce4dc86adad9c"
},
{
"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": "68d4455a2c920a74f69c98dc7708c337"
},
{
"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": "13923f3f83185d96de64b7d27e98a44b"
},
{
"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": "1d6331672fd0d9ec8f927327e87ebfbf"
},
{
"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": "86dc2e51c1d22d7c9056bac404838973"
},
{
"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": "72566217d1a9cf8dbcad16b0e047a627"
},
{
"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": "f74eeb3a6988f936f3b4e64fe0294540"
},
{
"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": "9bbd23cadd1557e93504f8d389174311"
},
{
"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": "57f2404d74bee42d7591fe8a1499d4d8"
},
{
"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": "254b8264012816998a333eb810665d9d"
},
{
"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": "89d0a43e43185d6b30a5ca99aede588a"
},
{
"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": "dabc09e01eefbec84d7badcedc82ad49"
},
{
"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": "25877bda315af43a1d949234141453f7"
},
{
"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": "8cb4ea5d9a3f7bcff24b430eb53a147e"
},
{
"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": "4f87bcc3185804c568f6414372a51747"
}
]
}