Gemma-Wukong-2bv1-q4f16_1-MLC / ndarray-cache.json
Kearm's picture
Upload folder using huggingface_hub
2253573 verified
{
"metadata": {
"ParamSize": 183,
"ParamBytes": 1409830912.0,
"BitsPerParam": 4.500347711112945
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 262144000,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
256000,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 262144000,
"byteOffset": 0
}
],
"md5sum": "0df787bcdc08d4792eab2601f7a02391"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "38809e07c773a53538e8ee568783222b"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 32772096,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
256000,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 32768000,
"byteOffset": 0
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32768000
}
],
"md5sum": "7a79b1fec36e129a32980ffa183127f7"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "04ce68e8314d8d88dcd689572cf162f6"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "f7d37391e98f9f1a12fc21c33c36867e"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 30482432,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 2097152
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 6291456
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 6295552
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 8916992
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 9244672
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 11341824
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 11603968
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 11608064
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28385280
}
],
"md5sum": "ca7530fc8c466ebfdc8c2d8d16592521"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "3c37eafe7dbd13930e461b7e86b376cc"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 32583680,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 0
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 4194304
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 4198400
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 6819840
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7147520
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9244672
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9506816
},
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9510912
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28385280
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32579584
}
],
"md5sum": "7ed3f8e1053fa15d84066d713de098c8"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "01eeda0a35c852b9c862da66136f0b4a"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 33431552,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 24186880
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28381184
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 28385280
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 31006720
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 31334400
}
],
"md5sum": "1d8bd7b542a6db13ccfb1feeb8cb98ea"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "4d5d73bee96dc9441047fe05fe2ff51f"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "92d1a0261da0f6a1ab9c0daacaeddcb0"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "898c0f0b09a4e65252e8670a39e1274d"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 30748672,
"records": [
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 0
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 262144
},
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 266240
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17043456
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 19140608
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23334912
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 23339008
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 25960448
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 28385280
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28647424
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28651520
}
],
"md5sum": "6a4c47f2592e6a2a24a9e2d52e380fb8"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "9b68b917de243b7c8f3a8763f7d902da"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 32583680,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 0
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 4194304
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 4198400
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 6819840
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7147520
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9244672
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9506816
},
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9510912
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28385280
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32579584
}
],
"md5sum": "7da702873448e3d4d1eff02df94aafcc"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "f7933e33915c46f863971774bca2037d"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 33431552,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 24186880
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28381184
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 28385280
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 31006720
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 31334400
}
],
"md5sum": "e8f50082023b18a9f1f63c063000b573"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "c795b4e1194cee8a3d9c46fe73bdd319"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "511c008568e45ce28ab1fd179c7d7237"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 32841728,
"records": [
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 0
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 262144
},
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 266240
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17043456
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 19140608
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23334912
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 23339008
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 25960448
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 28385280
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28647424
}
],
"md5sum": "9f6948c9a0b751e6280e8b782645e4c1"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "d7d360dd3a0f0de4c4b912a293d33d67"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 33431552,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 24186880
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28381184
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 28385280
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 31006720
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 31334400
}
],
"md5sum": "e9b8c270cc5280ec29e7f4f908f42854"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "0a55ffb6a71f8ba3e226007c01356e03"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "0a8c18ce73c7d08800dc0883bbe008b6"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "8f3a97a760189f133ad4a75b1ab08bf7"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 30748672,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 0
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 262144
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 266240
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17043456
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 19140608
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23334912
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 23339008
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 25960448
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 28385280
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28647424
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28651520
}
],
"md5sum": "dbde9eb9c7031f27bd2e8ba775a33f63"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "003deb4690a82c86a57f465c82c6d9ab"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 32583680,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 0
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 4194304
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 4198400
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 6819840
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7147520
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9244672
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9506816
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9510912
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28385280
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32579584
}
],
"md5sum": "9a40d939b4c0579059c769b2577e196b"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "0fdea51ca301d13b6062e5f2c8f38f4b"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 33431552,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 24186880
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28381184
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 28385280
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 31006720
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 31334400
}
],
"md5sum": "4b04b00c7d8ff893f43135a86e17b109"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "a7e869b9444ee84689f4d425550aa63c"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "c5061384861a44c5f7f9c31c0e2e2c9b"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "af8ee3cecdb42a2acd6f4303032247fb"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 30748672,
"records": [
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 0
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 262144
},
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 266240
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17043456
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 19140608
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23334912
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 23339008
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 25960448
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 28385280
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28647424
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28651520
}
],
"md5sum": "2e0f787f38f03557001add93643a268d"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "916844a47465c18ac666379ab52812bd"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 32583680,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 0
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 4194304
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 4198400
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 6819840
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7147520
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9244672
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9506816
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9510912
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28385280
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32579584
}
],
"md5sum": "6ed8107bf7ef39faa81ba825f0468912"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 24195072,
"records": [
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 24186880
},
{
"name": "model.norm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 24190976
}
],
"md5sum": "7d6ba444fa89b2e8c6b7a07c07241947"
}
]
}