Orion-14B-Chat-q4f16_1-MLC / ndarray-cache.json
Siyuan's picture
Upload folder using huggingface_hub
0bdcf7c verified
{
"metadata": {
"ParamSize": 486,
"ParamBytes": 8156712960.0,
"BitsPerParam": 4.50065789055498
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 216596480,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
84608,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 216596480,
"byteOffset": 0
}
],
"md5sum": "70fa49eb3c493d2b51677dd2c8c77761"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "b71502a403a980c670d6417e838740ff"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "099a4e0752317477cc9fadbb7df25589"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 32051200,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
84608,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 27074560,
"byteOffset": 0
},
{
"name": "model.layers.27.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 27074560
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 27084800
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 27095040
},
{
"name": "model.layers.27.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 32010240
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 32020480
},
{
"name": "model.layers.28.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 32030720
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 32040960
}
],
"md5sum": "1df1e2b812049ba6f9349c825d3cdcdd"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "77cdf350c414d4447ebed8384c81d1d4"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "d58bc20403e1b6c974ed3bcb98bd7fcd"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.28.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "d4b5ac1c5d910a699b7417469f66ddbf"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "cdd4e35f71c346e957c0709a99c6b27c"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "d8e5c5576272574911ee061347fa813f"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "9df59716db410f30a855dde87ba4e4a4"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.29.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.29.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "9d98fe072d0c0fb7593910ac098bd9a0"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "a60593c247608aa59b744908943a652c"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "63b125f3e073b22451b0bd0373a518e1"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "6783da5be01982b821f971e919ee1741"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.30.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.30.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "991e3d83e4f28c59bae264c1e9db84aa"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "3c502e17045d4668a017badca4f127fb"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "694e56e2339659b79e5a2a194cb49063"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.31.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "3fe027d0eef01938710756052104cb1e"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "66bebfc92e5a93f1d1c2f482b2ee9995"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.32.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "71a96d9a1f07362cf54cb2d0c6a07781"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.31.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.layers.32.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.32.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "c550cca627bf621e946b39f39d6d071d"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.32.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "d943f340920420e02f2f431b84a78279"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.32.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "92f25d779811c720d33465986d78e9f9"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.32.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.32.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.32.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.32.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.32.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.32.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "73a1ad6faf21063019c00fbe1e6860ce"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.33.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "f9cdf781669b9d2148669243fd1de04d"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.33.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "07f20d64dc98d02a0caa09911c3042de"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.33.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "e8e80ec38f0802ea41a5b74341cad51d"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.32.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.33.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.33.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.33.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.33.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.33.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.33.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.33.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "04689894836b6de2e5e25e745d1cc928"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.34.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "c9755cac9e4a05970cf8b4c54d798400"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.34.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "2438cb81ed0ca39088518692cac0eb6e"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.34.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "9b9aaabaa3dbad557ccc3725bdf0e546"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.33.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.33.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.34.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.34.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.34.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.34.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.34.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.34.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "ff7940e731cb68ea2df1fd4283b961a0"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.35.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "97e0daa3242a279df03b41cdc2d01a6e"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.35.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "f53e08036e38b3a50a59109bde03f20d"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.34.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.34.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.34.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.35.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.35.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.35.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "921faca7e31cdc19bcd39a64f3fb75d9"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.35.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "0b245add8688ca2cefb372ef93de811d"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.36.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "2aa12a0661f300a0303eab548df42419"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.35.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.35.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.35.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.35.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.35.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.35.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.layers.36.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.36.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "28d727ef81e4ea9a6460ea96610a201a"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.36.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "5eb6ed2785fb1a40ecc7ea84b8d8eda5"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.36.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "36923e2a78d9c2112fde1e3c23d86a25"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.36.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.36.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.36.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.36.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.36.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.36.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "78e4d9d4b36c726e315452ede0e3a2bf"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.37.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "bbee22a1fbf01e33eb6079c2aeff9489"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.37.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "adc91bc74c4fea6c703903d28b566820"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.37.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "8297ae53b1d5f2838c13de4aa1f6f453"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.36.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.37.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.37.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.37.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.37.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.37.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.37.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.37.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "8b673b122e1c03d8846abe30c8b5a13a"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.38.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "2e39fbaa85fae6bbc7b7386964ebb898"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.38.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "a40b2555465b5c9033c87f8abb8eb3bc"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.38.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "f6e293f82643fb36447895c0b125f08d"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.37.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.37.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.38.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.38.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.38.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.38.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.38.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.38.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "ce930ff5841ab91de2d5628f2e2e20c8"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.39.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "6839c5af229cce80221fd3ac9d5e3980"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.39.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "d2d272cc333436e03047a9e48167dcd8"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.38.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.38.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.38.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.39.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.39.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.39.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "5b46eb1f78894bf12d65b1620538ef93"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.39.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "f0ff10ef5b72dbd38c4e06a50d41495e"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 216596480,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
84608,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 216596480,
"byteOffset": 0
}
],
"md5sum": "b12b12d475642b24aa69fe7f811145ca"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 27074560,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
84608,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 27074560,
"byteOffset": 0
}
],
"md5sum": "d3aedbdc1b3affb80b03a3edbebcfcfd"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "58676650c2a0177eb91791e2e3f3f662"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 29552640,
"records": [
{
"name": "model.layers.39.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.39.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.39.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.39.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.39.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.39.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.norm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.norm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
},
{
"name": "model.layers.0.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29532160
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29542400
}
],
"md5sum": "8fa9999f9085ddfe0487829507329eae"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "696e4999f68069b1773a4b634476eb43"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "28a98790a89cea69405eaa61a097d8d5"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.0.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "21d046e1ac4c156ebfaac77193940e6e"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "a0f2b864212a0eae754053a85e8fd887"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "c01a91581f716055257b5eea881d88d2"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "27edefe8de27d0fb88687adeb9875d6a"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.1.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.1.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "3e42ee42193e2e0f52be9705255fd473"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "3b92dea68a4706d74ba07c0cdb8303cd"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "c0edf6488edb74dc00056c9646a30ccc"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "5d745b6f2194dda7562159e534ad7ed8"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.10.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.10.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "035ced7a8a755d1779cfcbebf2b5665e"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "6061241ba846fc109777435508196a5d"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "c74377d7b1dc83e40ecfce25e8565d6b"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.11.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "d028442b84182786570256a1bb75df29"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "3db854761d7988815ed0b5b19c08a676"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "06d8f8e18222a17e994824245810ec2a"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.11.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.layers.12.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "44dc1c5f2f6d6ca0db072b1a9156386a"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "b0d598c6d5caf3ffea3da4041ca9c4fd"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "c2d139c6799c020eaf446cfb2c468f8c"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.12.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "21e085295e2fb3d0716e023ff72d5073"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "7b04b723d0d4a5eb6ffeb69dc722001a"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "cc75a9359a950b46070babc5071be060"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "055e33be35d2d15ec39cc1c06f2c7684"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 26234880,
"records": [
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1638400
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 6553600
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 19660800
},
{
"name": "model.layers.2.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 21299200
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 21309440
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 21319680
}
],
"md5sum": "bf228d3c6b1b13be2de45dd45ab84f9c"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "6d6b0800daabfcf6de2e48fbe89a76a8"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "953f828afbfacb042403a1c0e281f313"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.2.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.layers.3.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "c73f26b86361722146e1fd2858e8ac63"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "e3bfd9c1b03734e1a3a3adc6a79caf27"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "053298a4f67158a12977323376042b8f"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.3.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "8dcf4c6fc615c26ca132c4c8ef8e35ef"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "74114f024b5d455a25cadb6c0b64e45b"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "04fe95b9e6179d9ea6328dbd514fbdc7"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "10a720cf64ec3849a93fdf092b432918"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.4.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.4.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "7e695a959754083c594e86c7cb655f3c"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "6ed0f1f5ff41a28d1fef8d801f33476a"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "98b82dd73af0021f80a78e40b639a840"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "1a6f23350bbeda005e74c780c0274e52"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.5.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.5.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "d1ee36f6ba4cd8d38e59c4abe5a2fc0c"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "012c3aa084a9b3a7366cc19cd26d0c34"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "ac1e3c90fb1d90d007827891575cc659"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.6.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "2ed276e374e3580d9b7bb4a23c0f46ad"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "4cc297258f87815f9af3a4abd60f9b2b"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "6d7bf648c1ca8584863d4a0f0019d9da"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.6.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.layers.7.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "09bdd7e7b420e62c9d5672087e88a4e1"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "867f82ef6eca182144a09b6d053d13de"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "e88c492ec7cf1881ad5c8563b362b795"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.7.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "a739b2696d01a7329e421a50b94813f1"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "070454efb31c28e8eacd50f917a4aa99"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "a39fdf6b59c55dc1fac36eb769b1b606"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "1222b913575c5f7afcfd05fe0d15c4e4"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.8.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.8.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "f95a110a56a9d9c0867d62740d91606e"
},
{
"dataPath": "params_shard_108.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "ecc2ce72ff58f04655c0ed66921e8592"
},
{
"dataPath": "params_shard_109.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "b5b490149dcf50b751db0aec1c8c37bc"
},
{
"dataPath": "params_shard_110.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "390d0db0775f566b0a192b183e736254"
},
{
"dataPath": "params_shard_111.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.9.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.9.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "5508c4901461c8d993789b33efb26d18"
},
{
"dataPath": "params_shard_112.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "766ce67be407c8bc6f83f0807e45d927"
},
{
"dataPath": "params_shard_113.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "a365b6a4700919d571a45e4bf70f5fde"
},
{
"dataPath": "params_shard_114.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.13.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "2bc1ceeec54d6a058531b00de70e78d6"
},
{
"dataPath": "params_shard_115.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "549a826fdf8a6c68d1e423a729ce6424"
},
{
"dataPath": "params_shard_116.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "ad5944451273a8cbec47ee2eda09d3ff"
},
{
"dataPath": "params_shard_117.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "ac479bb0491af3f0774a1665408e5022"
},
{
"dataPath": "params_shard_118.bin",
"format": "raw-shard",
"nbytes": 29552640,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.13.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.14.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9850880
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9861120
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9871360
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 14786560
},
{
"name": "model.layers.14.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 24616960
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 24627200
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 24637440
}
],
"md5sum": "795a8143a20c137aa07c65ffe14b71d2"
},
{
"dataPath": "params_shard_119.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "9142e05f652dae5e2c2372ffec89e5d8"
},
{
"dataPath": "params_shard_120.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "74d20534899606e17066e8ff29062324"
},
{
"dataPath": "params_shard_121.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "11c8740433b8c1f51cb409e13915d0c5"
},
{
"dataPath": "params_shard_122.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.15.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.15.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "30989a24c70060ce9076f35acb84f55a"
},
{
"dataPath": "params_shard_123.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "ca8eebe004bcfd4fd25b554a83a958cc"
},
{
"dataPath": "params_shard_124.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "327f8c0008b53ba83be8381fffdcfab6"
},
{
"dataPath": "params_shard_125.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.16.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "15d5eb568482fe144697c8268515da06"
},
{
"dataPath": "params_shard_126.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "48352aa580a98be6e314514c6c1647e9"
},
{
"dataPath": "params_shard_127.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "e389cec5d78ad7691b07acf98a3b1fad"
},
{
"dataPath": "params_shard_128.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.16.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.layers.17.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "96a8afd7946c2eeef876baa6e6a900bb"
},
{
"dataPath": "params_shard_129.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "90a188eb7f06b55f07ba4258bb121ba6"
},
{
"dataPath": "params_shard_130.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "8433d5b5f498748a5ce9168c9eb798fa"
},
{
"dataPath": "params_shard_131.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.17.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "88adde5dc7c74c200cc8c9ddabf819df"
},
{
"dataPath": "params_shard_132.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "f9397e1c4d4638f612825cacfa2a3bbd"
},
{
"dataPath": "params_shard_133.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "e6c662ca2784224f22ccb1f69e01d917"
},
{
"dataPath": "params_shard_134.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "ef8fc32c12744927409c1c59a3c7d11d"
},
{
"dataPath": "params_shard_135.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.18.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.18.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "8dd25925187de336ea714e2598863acd"
},
{
"dataPath": "params_shard_136.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "79a568ac1b181f91a3b614c0df148420"
},
{
"dataPath": "params_shard_137.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "585513860db114ce21936bddde7f79f8"
},
{
"dataPath": "params_shard_138.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "1b3fe359a919caf696d74d060c7e226b"
},
{
"dataPath": "params_shard_139.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.19.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.19.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "6acc007bfd202ee760a4840b071da2ea"
},
{
"dataPath": "params_shard_140.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "a48eb501044d82244e418a883d6e9f3a"
},
{
"dataPath": "params_shard_141.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "f79dddc2b1bbcdf5ba97fd240d75efaf"
},
{
"dataPath": "params_shard_142.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.20.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "b801c76ca26df2facd140de89e819cac"
},
{
"dataPath": "params_shard_143.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "e38d59f4d6b478220bac645a0f8344bd"
},
{
"dataPath": "params_shard_144.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "fb8ac52ef36643891a926a1edcc9c38f"
},
{
"dataPath": "params_shard_145.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.20.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.layers.21.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "672daa7a530b35036cc1ee32ce4d3e52"
},
{
"dataPath": "params_shard_146.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "1736324e2476c0cc5754b65860fb6a17"
},
{
"dataPath": "params_shard_147.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "a98197b4c802e71191efb2a2a8ce4a9a"
},
{
"dataPath": "params_shard_148.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.21.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "562091cb4a7a092dd8aecda7cc5942a2"
},
{
"dataPath": "params_shard_149.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "db3b9464484996caf94efca7949856a9"
},
{
"dataPath": "params_shard_150.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "0cf457e343dbbe2983513919621d7e3d"
},
{
"dataPath": "params_shard_151.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "9b41718d7fea52a31023f71d92ad7e7e"
},
{
"dataPath": "params_shard_152.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.22.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.22.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "2e1a20e8e0bf96026dd81a3d8723387c"
},
{
"dataPath": "params_shard_153.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "fd34b952e367fad5a96f24bf3befbc9e"
},
{
"dataPath": "params_shard_154.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "37a59c0a136a49447665631b2d484818"
},
{
"dataPath": "params_shard_155.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "3af32e1e1141cbbb5d8b6d19b5cef4b4"
},
{
"dataPath": "params_shard_156.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.23.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 19681280
},
{
"name": "model.layers.23.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "60c9e24914356ed670da8b74f2cc9c85"
},
{
"dataPath": "params_shard_157.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "b998f9ed7904fd7b61df322f38af4d01"
},
{
"dataPath": "params_shard_158.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "f991e611553d1a271a10ed8eefd86caa"
},
{
"dataPath": "params_shard_159.bin",
"format": "raw-shard",
"nbytes": 24596480,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 4915200
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 18022400
},
{
"name": "model.layers.24.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19660800
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19671040
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 19681280
}
],
"md5sum": "1919b77c2f6ffcb60f1d434e713c27c5"
},
{
"dataPath": "params_shard_160.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "9df12e7a0b9114236dd9a2839fbdeae3"
},
{
"dataPath": "params_shard_161.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "2aee3c096732f8fc551e18f99113b52b"
},
{
"dataPath": "params_shard_162.bin",
"format": "raw-shard",
"nbytes": 29532160,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 0
},
{
"name": "model.layers.24.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9830400
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 9840640
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 9850880
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 14766080
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 27873280
},
{
"name": "model.layers.25.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29511680
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 29521920
}
],
"md5sum": "df360b1be6c2aa4071b3f393d786fcd1"
},
{
"dataPath": "params_shard_163.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "70858c47d4874487841c716581c4ed73"
},
{
"dataPath": "params_shard_164.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "eec1828d499534b7c11c28643e5fa9ad"
},
{
"dataPath": "params_shard_165.bin",
"format": "raw-shard",
"nbytes": 32788480,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 0
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 4915200
},
{
"name": "model.layers.25.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 14766080
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 19681280
}
],
"md5sum": "98a328c294d6e0e2ab64378454a8f8e3"
},
{
"dataPath": "params_shard_166.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
5120,
1920
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "f3b106840d319d282775280f05c7da95"
},
{
"dataPath": "params_shard_167.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "1c802585e213ae828479e3ba42f04a07"
},
{
"dataPath": "params_shard_168.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "24ddd02fae8d864755722e4a3c397ff2"
},
{
"dataPath": "params_shard_169.bin",
"format": "raw-shard",
"nbytes": 21340160,
"records": [
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.26.input_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1648640
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
5120,
480
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 1658880
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 6574080
},
{
"name": "model.layers.26.post_attention_layernorm.bias",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16404480
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 16414720
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 16424960
}
],
"md5sum": "766966000253158ce0de1fc327083c40"
},
{
"dataPath": "params_shard_170.bin",
"format": "raw-shard",
"nbytes": 78643200,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
30720,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 78643200,
"byteOffset": 0
}
],
"md5sum": "7a23e189ebf5d3a69d85d32d1d09b9dc"
},
{
"dataPath": "params_shard_171.bin",
"format": "raw-shard",
"nbytes": 39321600,
"records": [
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
15360,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 39321600,
"byteOffset": 0
}
],
"md5sum": "e19131109e5e6f435f9cb381610be6ea"
},
{
"dataPath": "params_shard_172.bin",
"format": "raw-shard",
"nbytes": 29491200,
"records": [
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
30720,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 9830400,
"byteOffset": 14745600
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
15360,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4915200,
"byteOffset": 24576000
}
],
"md5sum": "e7bd7a7218b8efd7c48da852014c4530"
},
{
"dataPath": "params_shard_173.bin",
"format": "raw-shard",
"nbytes": 14745600,
"records": [
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
}
],
"md5sum": "e701a65564dd6cc1084451109859259c"
}
]
}