Hugging Face's logo

numen-tech
/
LLaMA3-iterative-DPO-final-w4a16g128asym

Model card Files Community
LLaMA3-iterative-DPO-final-w4a16g128asym / ndarray-cache.json
numen-tech's picture
numen-tech
Add weights
abad9bc
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": "1493e341b674c95e1c01f64c0ed3c870"
},
{
"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": "4c599804dbc249421ebeef8e8e493d79"
},
{
"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": "c0fa2b79fda9bfd57701e63ea875486b"
},
{
"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": "ee7a5c3d6cca523077d4a226d298a504"
},
{
"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": "d30a8831ee0611c0b41c07a218f04c7c"
},
{
"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": "fd5e91ec39f6836ac8d5b7d847020d3a"
},
{
"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": "0d19bee364afc2a1657a7d53f744652c"
},
{
"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": "3b9e396fbb58f53010a5cdfd6d74d0f9"
},
{
"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": "8e66cdd2ac484f083617e8820d076c75"
},
{
"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": "a5b2e7233c8c06da833f8b9b9974d3b8"
},
{
"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": "30fc5636cd7aa4e4cb1b3e481469e512"
},
{
"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": "b0069a0efa3b44be5e1a24ce81d14aa4"
},
{
"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": "d297039cff81c133c0ad328d9d2fd815"
},
{
"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": "ee312fdd44ef893704cf0e77fbfabb13"
},
{
"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": "de2e4be98cba2d923789bb95bd120246"
},
{
"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": "b31fcf01960838ad220504ed8e0b83e1"
},
{
"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": "d484c9b9effcdc58dde40d7d09afd7e3"
},
{
"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": "a8d4f87c3e73153801da231b3fb3a48e"
},
{
"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": "8d7a0e1ca3b0f68ef488f8db6de53df4"
},
{
"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": "ca58cb1c46463fe62457a4a2d92b5ae8"
},
{
"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": "7efd53ea04e914b44613f24d32f40c4e"
},
{
"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": "547544a6d74dcfe22f37d25c4a726ee8"
},
{
"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": "1d71da8806bdd69fd35b9bc9b1ca1e09"
},
{
"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": "d8922cc4526e12c66270c74bfad7b351"
},
{
"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": "9b4b6d485961f3d2abdecc3067525df0"
},
{
"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": "80eb96638bb47bc9e466ce36c3a0e3ba"
},
{
"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": "0ed98259fae7abef035c91ebf10f61ea"
},
{
"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": "c0242cb03770d4a1481fa0e5dae09a79"
},
{
"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": "aadff1093ccecec83818f4fdb5e947c3"
},
{
"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": "71d779302f894244022ed9f56671e4c9"
},
{
"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": "392bf10349f604f3d0d39b63ae8eb59c"
},
{
"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": "3e9ae133e636a282078ec0ea28066ba4"
},
{
"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": "34748f10c0f2e3a50b04ec388528f55d"
},
{
"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": "e8fed09e41ee0e866a78023bd571ae8a"
},
{
"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": "88257e0d0ca0348e8d1e0daddab08d2d"
},
{
"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": "db2e6136f7a750c21f066bb33311098a"
},
{
"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": "01bace24a2baf25e8741836cfe850c59"
},
{
"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": "fd5ce38c37af5750a11b6352b1e9cd55"
},
{
"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": "4fc54e3244b381666941a400007cf515"
},
{
"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": "65837576e68797446f8a17b12ff12e2f"
},
{
"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": "03955d706101bcdc6f99e63ecbd53d66"
},
{
"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": "1464dfd70172aefbf6289b45a6ca4762"
},
{
"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": "8c5494e7bad2bb8e8eff388508db1fe2"
},
{
"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": "1da82d1f9450471cc1e435ed3c08cfe7"
},
{
"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": "7afb24dc3677232364cabe211ebb160d"
},
{
"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": "89c8a61942fbe57a45cb3ca483af70e1"
},
{
"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": "70a0c5c938aec16803aca539951e0848"
},
{
"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": "9e678e7f59b153021730d8d2ba906825"
},
{
"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": "178a1d5be055f6303823c5383c1f87d6"
},
{
"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": "b574ac3b953d9979e7e9e4dcdff9e0ed"
},
{
"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": "d39cbd5a7d94b78d672196b7522c2063"
},
{
"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": "c48ab83ffa84f9f1b344242f93c7692d"
},
{
"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": "1c8f3ffd3192b521e31cd1181a4467b4"
},
{
"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": "1f593ea99a03b497e1d854fdca9e29b3"
},
{
"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": "29532e7f59e8751fda45ee044cff997f"
},
{
"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": "e52c3da098347fbe7c2102cc2ad6fc8d"
},
{
"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": "76821d287519c8eac751ee9a8e88ceae"
},
{
"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": "d1abcbca47e917f7542ae7544da3cd76"
},
{
"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": "a45d02b6ad128dfadc79a95c24b556d2"
},
{
"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": "5b53d7cf709082013e9bcd18b76fba5f"
},
{
"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": "2cc47fd1e5c923eb799fc8e524f89dc3"
},
{
"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": "f55000058a359a97961d53e71f9e8310"
},
{
"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": "55fa0ae4518cf91b21ac4eeef41da4ce"
},
{
"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": "9d4f6bb4c03d43ab852c3df66a164118"
},
{
"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": "fc41ac8ec8c50c17ad62f8116bf90bea"
},
{
"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": "4d2effdf35a8a9228e0bace507eb3b7f"
},
{
"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": "9d6425adcbc4d798f06eca0629663f95"
},
{
"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": "d12a8873ab5fba3410da4a173362c2d3"
},
{
"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": "65d2a752f7bba0d093b0d9cbb526bddf"
},
{
"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": "a2c380c6b3a72a488d0ee3a95ea4f150"
},
{
"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": "ae06ffa5d0bd402996dd61ac9628d76e"
},
{
"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": "18eab4a70c4ac02ba6aa795d352aec22"
},
{
"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": "0ec13266a8e28b1d0157699256a8a38e"
},
{
"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": "c7b31e7e91e403abce9e70889a1899c2"
},
{
"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": "2040647aa0f560b7d70da10d1ccd0c9e"
},
{
"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": "394362708321bc07ff9d6f601eb3f95e"
},
{
"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": "dbb6c13a2c85ab88f293352de823455a"
},
{
"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": "a687e27d702bccc76a22aadb41344a89"
},
{
"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": "df82de45f06cc1c72f1457fd7cabfbd6"
},
{
"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": "158f4c611e2ec305f8b111ed8e20a693"
},
{
"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": "eeaa0f6364eb29f8f8866427221b9603"
},
{
"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": "409331670e72e48524c192c758f4a3e6"
},
{
"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": "eb316e7b70aa758ddf4abe7f4cdda80c"
},
{
"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": "13d6d184a8fd187a9d8e497a430db1db"
},
{
"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": "6c62e13aaedd2282bba8fd71c699f43c"
},
{
"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": "3c7ea273c4d070599ad0626109b4fd21"
},
{
"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": "a3a184135a9385724bcf7a6e883bfbdd"
},
{
"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": "a77125b2ac67bf67f327193c1ff1381e"
},
{
"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": "80b809971b15ac02e7dd9ebd2b470e7f"
},
{
"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": "482ef0407905e35ba75812672a027188"
},
{
"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": "b2f3d5e96c3238e943a93ce55a6565e1"
},
{
"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": "421038708de6bda79ee4660b3dcedd36"
},
{
"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": "35ee6f9c0c45ab1ca6f69d19aec1e7b2"
},
{
"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": "2d5703b156c4ab227b598ffe22bfc4ce"
},
{
"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": "e0ab2475519b7d731a9d2e75020f527f"
},
{
"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": "0f9c3fb57fecc7c2446cb0ac5b3feb4d"
},
{
"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": "4f60ccf2a8e4ceb8c1c5cf206046c8a5"
},
{
"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": "30b601e9b0eac9f73437f6cb452c9dcb"
},
{
"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": "bd6f823b9d21f7fa7bba4b1e2bfe7b18"
}
]
}