Hugging Face's logo

numen-tech
/
merlinite-7b-w4a16g128asym

Model card Files Community
merlinite-7b-w4a16g128asym / ndarray-cache.json
numen-tech's picture
numen-tech
Add weights
2240a62
raw
history blame contribute delete
146 kB
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 3734447104.0,
"BitsPerParam": 3.033914104345779
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 65552384,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
32008,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 65552384,
"byteOffset": 0
}
],
"md5sum": "0ff66908c802b927175769bf5885dec4"
},
{
"dataPath": "params_shard_1.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": "1da184168dee60a5ca96258ec39ea868"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 33268224,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
32008,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2048512,
"byteOffset": 0
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 2048512
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 2056704
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3891712
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 3899904
},
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 3908096
}
],
"md5sum": "16978d27674712ab7433c9e7aa239dfb"
},
{
"dataPath": "params_shard_3.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": "05e59e50ad3d46416261816dc232672e"
},
{
"dataPath": "params_shard_4.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": "f9d71d22e4e97794c4ddf9cb709bc8e0"
},
{
"dataPath": "params_shard_5.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": "0556d3355dccd21a67f32e1f636f6e76"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 27156480,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 0
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 917504
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 2752512
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 2760704
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
6144,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 393216,
"byteOffset": 15343616
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 15736832
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 24125440
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 24395776
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 25313280
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27148288
}
],
"md5sum": "0a0b1e7a3709421f7fa8bf37a4d8477e"
},
{
"dataPath": "params_shard_7.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": "e5aa1493ce4c64b124d483475df1dbf3"
},
{
"dataPath": "params_shard_8.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": "7488cea0907a29cfcd3dc968639cfd8a"
},
{
"dataPath": "params_shard_9.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": "daecfa93a4c7102a8bba5b72998a8126"
},
{
"dataPath": "params_shard_10.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": "bf7d7f86629ec0bbabffa55c4b5687b0"
},
{
"dataPath": "params_shard_11.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": "f35f49523691d5e71becc07b5e5c9814"
},
{
"dataPath": "params_shard_12.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": "3273d769a660fa63c668642f15c8d53a"
},
{
"dataPath": "params_shard_13.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": "284ad6d5dc5e236377bda2daee0abdc8"
},
{
"dataPath": "params_shard_14.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": "6da26dbaee3532e9b923724178068bab"
},
{
"dataPath": "params_shard_15.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": "2d903a4af064854bb2c45326478eadf5"
},
{
"dataPath": "params_shard_16.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": "2d85b7564e18958aabb844e5969cf209"
},
{
"dataPath": "params_shard_17.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": "64b107fb882da346d501c30fdcc967b2"
},
{
"dataPath": "params_shard_18.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": "80cee6211355ec4de1696e35f33477fb"
},
{
"dataPath": "params_shard_19.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": "acc20ba266a0bd18d29631088e1c64b6"
},
{
"dataPath": "params_shard_20.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": "62698292cbe0536926dd385513294a8a"
},
{
"dataPath": "params_shard_21.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": "3d34fe66a86bbb9c9b7fef9cff563d44"
},
{
"dataPath": "params_shard_22.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": "ade46343834e68c8371663311c61b508"
},
{
"dataPath": "params_shard_23.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": "2e92872713226dc72811760194612398"
},
{
"dataPath": "params_shard_24.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": "3efa2a9648e1e3b97093886e60add82e"
},
{
"dataPath": "params_shard_25.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": "5d5d050a958075fd6ee40024f6a1f46b"
},
{
"dataPath": "params_shard_26.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": "c31a0a1485912b2322ad8eff507f2474"
},
{
"dataPath": "params_shard_27.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": "9a74d699af0b2aab542a791768d5431a"
},
{
"dataPath": "params_shard_28.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": "3e2da3fd54dbb459e25f33fcae7f5e36"
},
{
"dataPath": "params_shard_29.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": "9a970ebcea6a0829e2e878cc2fd096e9"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "7fedf7194774134328c3740fb09fd56b"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 65552384,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
32008,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 65552384,
"byteOffset": 0
}
],
"md5sum": "608f99a3f50e263ecb4fa717ddb9e131"
},
{
"dataPath": "params_shard_32.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": "0571e4a5e13623f1f99b341812077534"
},
{
"dataPath": "params_shard_33.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": "3c72a02dcd0bcbee262e685a1c9b54ab"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 26452480,
"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
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.embed_tokens.q_scale",
"shape": [
32008,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2048512,
"byteOffset": 21635072
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23683584
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 23691776
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 24609280
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 26444288
}
],
"md5sum": "9a3961be4d49ba9efe17e424cda143e6"
},
{
"dataPath": "params_shard_35.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": "63801dd9e6b0d4a7dddad23888577c26"
},
{
"dataPath": "params_shard_36.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": "819a6d0d223034ae76e28407706187aa"
},
{
"dataPath": "params_shard_37.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": "bdd13481c352254afc1b53ad65f8cf39"
},
{
"dataPath": "params_shard_38.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": "a8407c7dd93521e02bf56dcfc055295e"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 23461888,
"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.10.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 21626880
}
],
"md5sum": "b53d800ab27a70061a1c7a96f3054f78"
},
{
"dataPath": "params_shard_40.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": "118a75ff11ed12e1dc7273f32a1111f9"
},
{
"dataPath": "params_shard_41.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": "f18b057226d184f3a8a887c523a1dded"
},
{
"dataPath": "params_shard_42.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.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": "4a317f7916867c96b90cc73669050696"
},
{
"dataPath": "params_shard_43.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": "1cd19a2a4b58d59a9ea2f16697363b17"
},
{
"dataPath": "params_shard_44.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": "75fe15e40a629a63a820960c75a22c91"
},
{
"dataPath": "params_shard_45.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": "9c7badab5f86485b0454932d35942837"
},
{
"dataPath": "params_shard_46.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": "42c634438533d44898714d46d90d835a"
},
{
"dataPath": "params_shard_47.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": "ebfad18c917bc200080bd0ca411bf4dd"
},
{
"dataPath": "params_shard_48.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": "8baa526c472b10e29a28af1f9b4e572d"
},
{
"dataPath": "params_shard_49.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": "12d54d79702493ac17506093b1f1e287"
},
{
"dataPath": "params_shard_50.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": "88084d962ea1cb70bae613d96dce6ad8"
},
{
"dataPath": "params_shard_51.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": "78008fcf72afb8bded798125d480142e"
},
{
"dataPath": "params_shard_52.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": "dd0463e6229f17236ef340df822c4e71"
},
{
"dataPath": "params_shard_53.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": "8705b7136f2f0d41371e7fd267eab70e"
},
{
"dataPath": "params_shard_54.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": "b3ad50778036e6ee2381286160981218"
},
{
"dataPath": "params_shard_55.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": "b7ad1b9174f3f1782e92ad6b051eab77"
},
{
"dataPath": "params_shard_56.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": "ec4bc8834668fe6c5bc4217cc096ad41"
},
{
"dataPath": "params_shard_57.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": "05a1f8cdb759b0baaabc33ca1d2e1a31"
},
{
"dataPath": "params_shard_58.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": "4e48010d473b0df365d321aac199849c"
},
{
"dataPath": "params_shard_59.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": "574648a45929c66c0bec3298ffada7f3"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "9250ff39b1b4e9d3b733b919e08656e0"
},
{
"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": "9483e4406b7f24647759f07afb97f6c6"
},
{
"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": "3ff7c3243a50748ef9b8efaebffff5a5"
},
{
"dataPath": "params_shard_63.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.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 21626880
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21635072
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 22552576
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24387584
}
],
"md5sum": "10a32c6999616b98900c126f8be61a7d"
},
{
"dataPath": "params_shard_64.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": "e887c528f619fed07c9c45fbe36113f3"
},
{
"dataPath": "params_shard_65.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": "ce9c24fa1a40be573939fdc02e69b29a"
},
{
"dataPath": "params_shard_66.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": "85eb07522c11a15e0b324194832831b5"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 25329664,
"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.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.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22552576
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22560768
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 22568960
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
28672,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008,
"byteOffset": 23486464
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 25321472
}
],
"md5sum": "78afa88774a5617ce449154f6f7b454e"
},
{
"dataPath": "params_shard_68.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": "787951dbcdabafa1a39056e45962c508"
},
{
"dataPath": "params_shard_69.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": "4cc70de3171cedc99e6847e718ee1ae9"
},
{
"dataPath": "params_shard_70.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": "61913c38ad0a5c1c2f887c8067f1ea6e"
},
{
"dataPath": "params_shard_71.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": "33f50d9990f2aea855e74ea9eb00b561"
},
{
"dataPath": "params_shard_72.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": "84cd5e0e5fa8727e8bac7454b46f0174"
},
{
"dataPath": "params_shard_73.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": "1b18e741984849cc20019fa02ecaa36d"
},
{
"dataPath": "params_shard_74.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": "37834aeb84432828f0d1c24a6e3d3f09"
},
{
"dataPath": "params_shard_75.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": "708df524f43a0aa5bc942ede7a35d674"
},
{
"dataPath": "params_shard_76.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": "88313904e3f3dc5c24a85be85d8bc9e3"
},
{
"dataPath": "params_shard_77.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": "2013a47c0dd63c68bb4e9b739ccf6b9c"
},
{
"dataPath": "params_shard_78.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": "a782e1a2eb0159409b8e3e8dfc84e7d8"
},
{
"dataPath": "params_shard_79.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": "651a568c80e0cec7e88aad9720b0cb22"
},
{
"dataPath": "params_shard_80.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": "6acc47be19b3791d197bd9a7b550c671"
},
{
"dataPath": "params_shard_81.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": "d5b57305596d4df154eaf256e64494a5"
},
{
"dataPath": "params_shard_82.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": "a31160f90b6c7ad57142d729a6330935"
},
{
"dataPath": "params_shard_83.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": "3e57fa451d4c74e05c472a0048a0807a"
},
{
"dataPath": "params_shard_84.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": "e714dbf2fea3363084651749f9c09af4"
},
{
"dataPath": "params_shard_85.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": "c42d8ef1fc1e9dbc2eb6f9f8604ef74c"
},
{
"dataPath": "params_shard_86.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": "38362cbe59fc546806709a84d5781448"
},
{
"dataPath": "params_shard_87.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": "8982e2bdfbb7e778c82cdd105339a5d5"
},
{
"dataPath": "params_shard_88.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": "8892818ad7d95741ead12cbe3aa1c115"
},
{
"dataPath": "params_shard_89.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": "dbafc42a6545a7df36b1c9468be685d1"
},
{
"dataPath": "params_shard_90.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": "81a051eaf62368923df3774d0c23d0db"
},
{
"dataPath": "params_shard_91.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": "2d003528fd04609896bd07678b560a47"
},
{
"dataPath": "params_shard_92.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": "3e7795e8b941d0df2f1eb38bee178499"
},
{
"dataPath": "params_shard_93.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": "6059afedec79210054b02b09d3e19e84"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 24395776,
"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.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": "0c7bed6efe0e873af69c06b9cac5a682"
},
{
"dataPath": "params_shard_95.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": "bd8c6eac86568f9dabed5c0194f7ec04"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 22544384,
"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.mlp.down_proj.q_scale",
"shape": [
4096,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 917504,
"byteOffset": 21626880
}
],
"md5sum": "c72f8f10c0c918370e9325a84a80e9b3"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 21626880,
"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
}
],
"md5sum": "242815e566a444645f5d1d2b864c98b9"
}
]
}