Hugging Face's logo

mlc-ai
/
internlm2_5-20b-q4f32_1-MLC

MLC-LLM
web-llm
Model card Files Community
internlm2_5-20b-q4f32_1-MLC / ndarray-cache-b16.json
riczhou's picture
riczhou
Upload folder using huggingface_hub
acce4d2 verified
raw
history blame contribute delete
238 kB
{
"metadata": {
"ParamSize": 485,
"ParamBytes": 12415229952.0,
"BitsPerParam": 5.00081018149736
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.0.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "00284ef2b463215cfc463010f321b10f"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.0.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "3b629921bccee1f0d0fc4a28c3738425"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 24391680,
"records": [
{
"name": "model.layers.0.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
},
{
"name": "model.layers.0.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18874368
},
{
"name": "model.layers.0.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21233664
},
{
"name": "model.layers.0.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24379392
}
],
"md5sum": "527f54d68f1391943cd99ba6f0766995"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.0.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "6b852c980e98d1be149c8f25702e5edd"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.1.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "594cc542e523dd583dd0f4b4d5433018"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.1.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "72f358e79b8ce3ad26cbff27d21c110d"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.1.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "567766e2e606b1504409bc05ce25d986"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.0.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.0.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.0.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.1.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.1.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.1.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "5f6af20d76b092e2eae713d51d0b2316"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.1.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "8e0ee16703bdc83a3cc171acb83ece87"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.10.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "8c19ae1b402ca35373381209750ac083"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.10.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "ea35bfabe8ebe4ce81194879887850d3"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.10.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "4984b3a8a93f30161828ddcdf8c4726c"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.1.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.1.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.1.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.10.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.10.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.10.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "e0c94f7240178fdb1665d8b03d267700"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.10.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "3a973332765dd568c26ceac7ea6a0e7b"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.11.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "b70e1be8b131f50c6018dec9516dc17a"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.11.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "ebe5a55987f64f40370cf5a583dd38d6"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.2.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "50d46afa2c2b532d0a4c37bbb6be9236"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.2.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "89b43a668dc71a4c594f041b76a1f08a"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.2.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "72c1c5a128357d38e90668edb2268f7a"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 29908992,
"records": [
{
"name": "model.layers.10.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.10.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.10.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.11.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.11.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.2.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 24391680
},
{
"name": "model.layers.2.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 26750976
},
{
"name": "model.layers.2.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 29896704
}
],
"md5sum": "6078e600ba0de2bc58adab9d7e918f49"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.2.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "ac3c4d8201252cb948e38c0e8871ac2f"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.3.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "9c69a111df96a3fc79aea18b618a916c"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.3.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "e9c01a19332e2adb930db683e530c91b"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.3.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "5479be3e34bd3a18e63ebe8977c0a65e"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.2.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.2.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.2.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.3.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.3.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.3.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "6eb8bda82655d3df6c83bb20e4713205"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.3.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "95c51f5f4fc1b7fcb98398b65b7c5d4a"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.4.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "0b84b0a3d48c305df2d7a5c22bbd4f20"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.4.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "f24d75e5c16f85904f8c8c29b57481f2"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.4.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "5e15002174167919e1eda921c51fba38"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.3.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.3.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.3.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.4.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.4.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.4.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "b4deb97fd05b39bbffa1c05a7343217e"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.4.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "26e160d3918d689f35da649de61c7230"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.5.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "349eb6d5eed5399e5e1afa68877e889f"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.5.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "160c6446975d5ceaa6372e00f250db8b"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.5.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "25558c41244691ea68e5e1cd29484abd"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.4.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.4.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.4.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.5.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.5.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.5.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "55629761943083ef1bdadb84097efc38"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.5.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "802e9ddc7310e14dd8664de74c12e6bd"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.6.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "8ca404a2c8262e6448e729724bf99ae3"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.6.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "22ce86177afd884ee20dae0bebc6c106"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.6.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "86f1c3c9305d018f5132a7e790a4d7cf"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.5.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.5.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.5.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.6.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.6.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.6.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "6abbaee8380fba70014b21eb525acd62"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.6.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "bf41cd47c2e835e2958c022cd42ee082"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.7.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "83fdea8e34ce86e90af2c0723109482d"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.7.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "44a2698b1f84e642c12209710a00c86c"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.7.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "ec1a742c6dd4bfb50a52719bcbe4a6f2"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.6.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.6.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.6.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.7.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.7.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.7.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "f11f38d92a05c8e64f353a2c8b1ef96b"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.7.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "330b2c9435023374d015775f9631c0eb"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.8.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "a9d75c8ee5f764d31903e266462838b8"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.8.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "d72ca566fddb54ead1fcdff8b7b53d36"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.8.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "43fe8e433180a84ed4add127feb489e0"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.7.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.7.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.7.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.8.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.8.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.8.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "1bcaabd831c6df949af2a2c99aa391d6"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.8.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "f7eeaed1e2fd0d650d3adbbc3d70d62f"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.9.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "2850456422dafdf6a3ad21583b83ea94"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.9.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "06d0e7a00ed7d447049d328ebbc27a56"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.9.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "eff8f28665fb3d94927a4d690128db69"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.8.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.8.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.8.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.9.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.9.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.9.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "10d45a0386cd768f1a38bc9c99118bf4"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.9.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "8f50250f4d015cebf33c51e550a6a558"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 284295168,
"records": [
{
"name": "model.tok_embeddings.q_weight",
"shape": [
92544,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 284295168,
"byteOffset": 0
}
],
"md5sum": "2dd9e7b5161e20e4d85dee74ae980199"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 35536896,
"records": [
{
"name": "model.tok_embeddings.q_scale",
"shape": [
92544,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 35536896,
"byteOffset": 0
}
],
"md5sum": "966f48b841b8d678e03e9806709d63b5"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.11.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "74af130ac4fb9d8caf5af3fbd80ca161"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.11.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "4dbe32af3028d2ab8ed626982b3f3a7b"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 31481856,
"records": [
{
"name": "model.layers.9.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.9.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.9.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.11.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18886656
},
{
"name": "model.layers.11.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 18898944
}
],
"md5sum": "437c70592dbff13eb274e84dc5d475f7"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.12.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "103bd4315c0d5e8b1f6e02608ce71648"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.12.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "96ad9f6264c30961b8bb9d8322ff028e"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 30695424,
"records": [
{
"name": "model.layers.11.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 0
},
{
"name": "model.layers.11.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 6291456
},
{
"name": "model.layers.12.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 6303744
},
{
"name": "model.layers.12.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 25178112
},
{
"name": "model.layers.12.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 27537408
},
{
"name": "model.layers.12.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 30683136
}
],
"md5sum": "ac0bb20f0cf8e930e7c25bf5476bf21b"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.12.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "b1f5ecb6ca96f6c06f4ed28fbf03facd"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.13.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "5788364a5bc1e426c0092ba506ac88ae"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.13.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "476632fb1c35b3ffb77d627532bc03f7"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.13.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "758524bcd105b05f63a5d71827b66f26"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.12.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.12.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.12.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.13.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.13.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.13.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "379cd71d453310281511d95f270432c3"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.13.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "1b103cb0357b37228f103c6c5699916d"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.14.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "bd26f1a288dd8d21399fc51e72729e8d"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.14.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "c649c1685be04409e8bbdc07011fa517"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.14.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "de8b0d86bf134e76ceea123cf3f14d8e"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.13.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.13.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.13.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.14.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.14.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.14.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "a9a9a45b14236a23be37135a86032e5d"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.14.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "9f2b7ecb18020990fd511a92ff38d340"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.15.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "108d512f0cf4571de9606b20b69dde22"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.15.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "e1c7bbe39bfe6f291da451e622c81313"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.15.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "cf1911680f3663ef1f8d93bf95d37d22"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.14.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.14.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.14.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.15.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.15.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.15.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "7dbefcf306cf30966fdeaaa6c94ec116"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.15.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "733df901831944e32ccf825060952406"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.16.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "4a20b7ea01b63d1ca1b2fa6421a1a989"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.16.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "77dde9b3f4c9684e5483377fd769b1ec"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.16.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "5d7a7756a94ea7bc8b9947d232e5024d"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.15.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.15.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.15.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.16.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.16.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.16.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "ab796d825f8dc85dab90b1b00d7aa872"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.16.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "c532bfe59af4beb0f13aa56cbe83a2de"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.17.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "ccb30288735bf955a97f4766013dfe37"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.17.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "0e60341ce11dc8ba45ea124c3a000292"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.17.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "0cc2e84cdb8c75cb866a0e18cd872df5"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.16.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.16.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.16.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.17.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.17.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.17.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "36b48b2a9c1c14b98b37d468c6cde1b8"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.17.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "9431304c21d6bd745182e0bb9e9c1c0a"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.18.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "7258e48041c8a95042ba5e36f8419057"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.18.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "83788a9066bdff886784a464d6cf8b50"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.18.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "1f65a4aa2a217b8e01ca0e4a3393ec01"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.17.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.17.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.17.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.18.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.18.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.18.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "bb84c0a28cee4cec53007b013706031c"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.18.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "7f0b46d5af70c4e5e051921e8575dae9"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.19.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "d34443174a1d161d011b75c4622320a1"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.19.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "5f587454560db68552c91c80e8a2167e"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.19.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "cc41aac634822122e1b812cf09b4fd3b"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.18.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.18.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.18.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.19.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.19.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.19.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "bd879f531d67097cacc6f66e6013bc6a"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.19.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "4159726292aab97f45285779b4cbec30"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.20.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "43c5d41337bff9653e51d5a779fbb65a"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.20.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "c3691a094aa91939df7dec2371809d94"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.20.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "f50853b2db64dff9649305daddf299e6"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.19.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.19.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.19.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.20.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.20.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.20.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "076edf9a22f10c86d2e0aa1134480f0a"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.20.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "314871849addd0914a61470d09c00d3e"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.21.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "61ea95ad988deab855b1eeecf346fda1"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.21.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "63987ea2ffccc21c68679cf17435f48b"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.21.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "2b17fc37892c02d03b97eef6f4dc561b"
},
{
"dataPath": "params_shard_108.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.20.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.20.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.20.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.21.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.21.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.21.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "90688941650e245560cefb7e210f76fe"
},
{
"dataPath": "params_shard_109.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.21.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "821d9bb73d369855fa894f78f35aefee"
},
{
"dataPath": "params_shard_110.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.22.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "2a11fe75c93f2ddae9902abbac674422"
},
{
"dataPath": "params_shard_111.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.22.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "dd20a56a827c8f7e860cb11b28cd2b7d"
},
{
"dataPath": "params_shard_112.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.22.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "2447c5f423bded8419a81e9991f572f3"
},
{
"dataPath": "params_shard_113.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.21.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.21.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.21.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.22.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.22.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.22.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "6eae2ad8eee54be7f63bde100fb62231"
},
{
"dataPath": "params_shard_114.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.22.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "5b24f426958c6b855f6f95e14d9be139"
},
{
"dataPath": "params_shard_115.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.23.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "c9cc3230c3c027b10e80dff08adf0a78"
},
{
"dataPath": "params_shard_116.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.23.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "29eba1a47dc1cf87f59b0fade436b543"
},
{
"dataPath": "params_shard_117.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.23.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "f678b6d832024e53015816cc5ec51072"
},
{
"dataPath": "params_shard_118.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.22.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.22.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.22.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.23.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.23.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.23.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "5b7189b7f51a5b171674a76a1d75f691"
},
{
"dataPath": "params_shard_119.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.23.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "508ca62f0bcfcfc8280bcbc2494c32ae"
},
{
"dataPath": "params_shard_120.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.24.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "de1db8eb1512766e7fa21d2cdfacdb70"
},
{
"dataPath": "params_shard_121.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.24.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "6a955051ad2bfd366a96d81b9c560ab5"
},
{
"dataPath": "params_shard_122.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.24.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "ea0c959128e9ee2cc6c32a746b8ff09e"
},
{
"dataPath": "params_shard_123.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.23.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.23.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.23.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.24.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.24.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.24.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "8622abdc949e2d88b54cafc655de47ce"
},
{
"dataPath": "params_shard_124.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.24.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "f434f5e3991c9c9c9882af18be749fc4"
},
{
"dataPath": "params_shard_125.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.25.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "ec461d88c4fc6a212eca45c40e65cbab"
},
{
"dataPath": "params_shard_126.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.25.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "e68d544dab45df74293e70ef03f944da"
},
{
"dataPath": "params_shard_127.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.25.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "87a9d5e7eaae4e259628990035d8fa41"
},
{
"dataPath": "params_shard_128.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.24.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.24.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.24.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.25.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.25.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.25.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "e3402b08f43ad28de2dd036b76aac55c"
},
{
"dataPath": "params_shard_129.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.25.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "aa4fa4a1c0cdd8bb3959d247b3caa895"
},
{
"dataPath": "params_shard_130.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.26.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "3c997ac7ad8859dd5662cc4fa65e1f59"
},
{
"dataPath": "params_shard_131.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.26.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "98808696bd17e3f4877f94ae57de66c6"
},
{
"dataPath": "params_shard_132.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.26.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "cf1f5dc59f4545d3e3c7533da0985c35"
},
{
"dataPath": "params_shard_133.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.25.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.25.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.25.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.26.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.26.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.26.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "35ba152aed7d162d2fd0905c55dfda71"
},
{
"dataPath": "params_shard_134.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.26.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "76bbf8feb812602034633b441c4c1bdd"
},
{
"dataPath": "params_shard_135.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.27.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "cd146a5eaddc8cf1ffdd72605a2dbed9"
},
{
"dataPath": "params_shard_136.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.27.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "76c6d0263361b79ffe484451392e2922"
},
{
"dataPath": "params_shard_137.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.27.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "4f79215a5d111ace561aba58dc90e569"
},
{
"dataPath": "params_shard_138.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.26.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.26.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.26.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.27.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.27.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.27.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "6e975e2691c59495fc857fcacdc73b28"
},
{
"dataPath": "params_shard_139.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.27.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "fae53a3d7c2d52f056ae6f33822cabdd"
},
{
"dataPath": "params_shard_140.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.28.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "531d3a4c2b5e041de61c91eec2d3722a"
},
{
"dataPath": "params_shard_141.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.28.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "cf46185cbf1b28ee4a03134026850c60"
},
{
"dataPath": "params_shard_142.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.28.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "f862e7fdf14a772a2da0102aaa8bf143"
},
{
"dataPath": "params_shard_143.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.27.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.27.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.27.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.28.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.28.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.28.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "9db0f23fddffbc788735d8d0aa57640b"
},
{
"dataPath": "params_shard_144.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.28.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "df553356a969c3a737f939eb62054831"
},
{
"dataPath": "params_shard_145.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.29.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "14eb5b5bcdd58ae0c9dd47e74dcbe759"
},
{
"dataPath": "params_shard_146.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.29.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "9f612732a5cb843c4a9379968982dbf7"
},
{
"dataPath": "params_shard_147.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.29.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "f433aa0734aa232dbc0cc812baf6daeb"
},
{
"dataPath": "params_shard_148.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.28.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.28.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.28.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.29.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.29.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.29.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "5ec13f3c8e9ad06b997ec4ee954d7d97"
},
{
"dataPath": "params_shard_149.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.29.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "b55d6c5b4e3cbb41768a50882e51ab3d"
},
{
"dataPath": "params_shard_150.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.30.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "96d71035e4dfaa23cf672fcf4b3148ad"
},
{
"dataPath": "params_shard_151.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.30.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "281351522900e1ed0f106ddc5ffa26e8"
},
{
"dataPath": "params_shard_152.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.30.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "726e8a7f835904c85aad54423c7d3a40"
},
{
"dataPath": "params_shard_153.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.29.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.29.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.29.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.30.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.30.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.30.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "254c3ebe5fe7dcc4e5dd795067317b82"
},
{
"dataPath": "params_shard_154.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.30.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "6ef2ba1ad4d1453c184fb1c7319dd9c7"
},
{
"dataPath": "params_shard_155.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.31.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "d0c9317ba5f9aaa4416fe68e45ded617"
},
{
"dataPath": "params_shard_156.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.31.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "a477bd5fcdd32c040bc0dbae50b93df5"
},
{
"dataPath": "params_shard_157.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.31.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "c79299422f56a51832f8f360150dd81e"
},
{
"dataPath": "params_shard_158.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.30.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.30.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.30.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.31.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.31.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.31.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "807d4a9725b140f5bf95136c137ad4a4"
},
{
"dataPath": "params_shard_159.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.31.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "ef1ed74e341ae11b4b4a3ddc66eb15d4"
},
{
"dataPath": "params_shard_160.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.32.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "89b29e5f3381e40d07d146cb9086257d"
},
{
"dataPath": "params_shard_161.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.32.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "1c8a97f5ae3599ec917df53f247c32e1"
},
{
"dataPath": "params_shard_162.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.32.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "8e0b40b7c224f8d23e2bbd05feed1afa"
},
{
"dataPath": "params_shard_163.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.31.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.31.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.31.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.32.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.32.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.32.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "7eff74f813c073ff0fd6b021f80ff545"
},
{
"dataPath": "params_shard_164.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.32.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "03bdb41601a66ec7c43350268194c94a"
},
{
"dataPath": "params_shard_165.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.33.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "f852fcb989a6edd819f494af113e36f6"
},
{
"dataPath": "params_shard_166.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.33.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "e0acce77d092085f687864e55bc5a359"
},
{
"dataPath": "params_shard_167.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.33.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "eea08e28000c1cfe5410d6e7dfa7b1df"
},
{
"dataPath": "params_shard_168.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.32.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.32.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.32.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.33.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.33.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.33.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "12def825c7928f5e1179ee5647ce8415"
},
{
"dataPath": "params_shard_169.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.33.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "14bd5dc653fdc418cbc7224efd42c0e6"
},
{
"dataPath": "params_shard_170.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.34.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "75c058b004e1529ac64ac26e2d34eb9a"
},
{
"dataPath": "params_shard_171.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.34.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "33695918d34627539c8ce45c7d48a898"
},
{
"dataPath": "params_shard_172.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.34.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "628a63573d1bac6ef42b55f38b0d1940"
},
{
"dataPath": "params_shard_173.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.33.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.33.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.33.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.34.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.34.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.34.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "f31fb49e035888712b297475c52864b2"
},
{
"dataPath": "params_shard_174.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.34.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "d2eb378861bc29d98bafface5ab066db"
},
{
"dataPath": "params_shard_175.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.35.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "31503682e00d6487b61f43a21b25bf8f"
},
{
"dataPath": "params_shard_176.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.35.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "567fbde9ba586cbd71a37fb9b6af50df"
},
{
"dataPath": "params_shard_177.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.35.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "d2eedaadc51dc8692cf212161cbef3a6"
},
{
"dataPath": "params_shard_178.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.34.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.34.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.34.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.35.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.35.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.35.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "69b518ec54f6677fcd919c9253b0614e"
},
{
"dataPath": "params_shard_179.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.35.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "3983774f8fc3f7c182befdaf92183fcf"
},
{
"dataPath": "params_shard_180.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.36.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "cfc73b0d1f4316f639b608ba09c60df7"
},
{
"dataPath": "params_shard_181.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.36.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "ef8bb46de2ff642420174496ff8eb9e9"
},
{
"dataPath": "params_shard_182.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.36.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "3705cfbda7b10118d52053e4bcf5b53b"
},
{
"dataPath": "params_shard_183.bin",
"format": "raw-shard",
"nbytes": 24391680,
"records": [
{
"name": "model.layers.35.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.35.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.35.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.36.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.36.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
}
],
"md5sum": "60d7d3b3348e08fa93bfc93a92843e35"
},
{
"dataPath": "params_shard_184.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.36.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "dea2c5c8e8f65bae170d749819af3b84"
},
{
"dataPath": "params_shard_185.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.37.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "f8abc7a7c35584caee36d6ca34d41d5e"
},
{
"dataPath": "params_shard_186.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.37.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "1c5f3d415b4decb3a935aadf5f74f6a8"
},
{
"dataPath": "params_shard_187.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.37.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "234b8f8209919d4e786b83e0a48f1a53"
},
{
"dataPath": "params_shard_188.bin",
"format": "raw-shard",
"nbytes": 24416256,
"records": [
{
"name": "model.layers.36.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.36.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 12582912
},
{
"name": "model.layers.36.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12595200
},
{
"name": "model.layers.36.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18886656
},
{
"name": "model.layers.37.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18898944
},
{
"name": "model.layers.37.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21258240
},
{
"name": "model.layers.37.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24403968
}
],
"md5sum": "f9a0414ec40d9bf8560cde85f764a729"
},
{
"dataPath": "params_shard_189.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.37.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "caadc9898fa702e45d7a8066d6fc034b"
},
{
"dataPath": "params_shard_190.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.38.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "daca59f2befcbf65ca4f22132e1f5968"
},
{
"dataPath": "params_shard_191.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.38.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "a64ed9dfed562df2a47360291349c392"
},
{
"dataPath": "params_shard_192.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.38.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "16560fdb4bf490a9f510a99d03ae7f65"
},
{
"dataPath": "params_shard_193.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.37.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.37.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.37.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.38.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.38.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.38.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "e9776f6d848093cd8ae111d82c5470f0"
},
{
"dataPath": "params_shard_194.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.38.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "f83f4681d5135acfefeaed331013a245"
},
{
"dataPath": "params_shard_195.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.39.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "79262a1b152d0c6dac9b81bd23c4b732"
},
{
"dataPath": "params_shard_196.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.39.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "494adcfe5d06195f184c89b9641b7b02"
},
{
"dataPath": "params_shard_197.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.39.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "2f0a0694e12495696d67af7793e52814"
},
{
"dataPath": "params_shard_198.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.38.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.38.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.38.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.39.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.39.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.39.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "b6fb3b57ef9e289ee317fad962a27274"
},
{
"dataPath": "params_shard_199.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.39.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "ef20c9cd3ace2631ee57f473491ee84f"
},
{
"dataPath": "params_shard_200.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.40.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "00ba24af7ddee4fd0df90052c80006f6"
},
{
"dataPath": "params_shard_201.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.40.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "dddc0f57281ddfe8175f7f7de227bc4f"
},
{
"dataPath": "params_shard_202.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.40.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "0e8af89ea7ad941c3495e95cd4946df5"
},
{
"dataPath": "params_shard_203.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.39.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.39.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.39.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.40.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.40.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.40.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "cb2b6d03e66660fdea2851e6d6242f62"
},
{
"dataPath": "params_shard_204.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.40.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "2ad00ee80dea62083d12480dff27142f"
},
{
"dataPath": "params_shard_205.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.41.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "8bbdf2b4613d4d2492b52721519e0330"
},
{
"dataPath": "params_shard_206.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.41.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "5853bdf385a2cf95cbb546d8a60f52e6"
},
{
"dataPath": "params_shard_207.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.41.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "86b8a754afa6b098fd4da8c5adf2bbde"
},
{
"dataPath": "params_shard_208.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.40.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.40.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.40.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.41.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.41.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.41.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "8072f10fc32633f7ef13f12284581bfd"
},
{
"dataPath": "params_shard_209.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.41.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "dce2c7f9765e1bf49f7cffa2f44d9980"
},
{
"dataPath": "params_shard_210.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.42.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "38f4c827a9da73a327a03a672fdb3864"
},
{
"dataPath": "params_shard_211.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.42.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "2ac7f290ce44fd7fc72ac4b663e35c17"
},
{
"dataPath": "params_shard_212.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.42.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "b1a74c2b552d5f35279c762744e5dfe8"
},
{
"dataPath": "params_shard_213.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.41.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.41.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.41.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.42.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.42.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.42.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "1bb78ce0fedee9d4f4685ecd4bbc0baf"
},
{
"dataPath": "params_shard_214.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.42.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "aac7ba81c61f2aed1b363f37c9ff9b1d"
},
{
"dataPath": "params_shard_215.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.43.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "6ae3315184976b9bb3dbf4c97a8eb7a1"
},
{
"dataPath": "params_shard_216.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.43.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "26b7bf85fe6a4013122193df0e1dbc6c"
},
{
"dataPath": "params_shard_217.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.43.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "80d536ada8406f0655c2895a1700fac8"
},
{
"dataPath": "params_shard_218.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.42.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.42.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.42.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.43.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.43.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.43.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "d3445886e6570c376d9b9a53f0b1e822"
},
{
"dataPath": "params_shard_219.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.43.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "8f90ce24a00118439f3ccb44a0e25280"
},
{
"dataPath": "params_shard_220.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.44.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "00000f7db76c8343c8e1fc3ac220a7ac"
},
{
"dataPath": "params_shard_221.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.44.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "116acd05f0ea0602a2b1294c7862986b"
},
{
"dataPath": "params_shard_222.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.44.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "a712ed019202c2f1ad61188e5a22eb4c"
},
{
"dataPath": "params_shard_223.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.43.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.43.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.43.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.44.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.44.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.44.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "3aba4040778ad5da5bb7bfdb11c30159"
},
{
"dataPath": "params_shard_224.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.44.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "2efc16c7b850c4a57d64f37b0e0d26d0"
},
{
"dataPath": "params_shard_225.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.45.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "e9cf7537c22a75aaf83b658a94d08bb0"
},
{
"dataPath": "params_shard_226.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.45.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "4889b75762a9e488476c7ec782ac2756"
},
{
"dataPath": "params_shard_227.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.45.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "e27715da69d6d827ed0489a1b24c7479"
},
{
"dataPath": "params_shard_228.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.44.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.44.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.44.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.45.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.45.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.45.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "e057dbb01489145de195eb4f848fb468"
},
{
"dataPath": "params_shard_229.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.45.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "73c091f28524a94856dc84ee54dc8765"
},
{
"dataPath": "params_shard_230.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.46.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "a098d1d326bd7e64488b230a35914a4b"
},
{
"dataPath": "params_shard_231.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.46.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "5ed98589f051eb6185235ebddd8f8bef"
},
{
"dataPath": "params_shard_232.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.46.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "e62a203a74743c9f2b17d31a82f2ca7e"
},
{
"dataPath": "params_shard_233.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.45.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.45.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.45.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.46.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.46.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.46.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "1ddffa454715f1f5cc29c7c4047d7bc0"
},
{
"dataPath": "params_shard_234.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.46.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "f7803532c3933b7164ea4818c95477c4"
},
{
"dataPath": "params_shard_235.bin",
"format": "raw-shard",
"nbytes": 18874368,
"records": [
{
"name": "model.layers.47.attention.wo.q_weight",
"shape": [
6144,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18874368,
"byteOffset": 0
}
],
"md5sum": "3d3343c87f3a48d5f8402b2fc7332c73"
},
{
"dataPath": "params_shard_236.bin",
"format": "raw-shard",
"nbytes": 25165824,
"records": [
{
"name": "model.layers.47.attention.wqkv.q_weight",
"shape": [
8192,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25165824,
"byteOffset": 0
}
],
"md5sum": "7765eac572da6689c28cfbb5bdcbe598"
},
{
"dataPath": "params_shard_237.bin",
"format": "raw-shard",
"nbytes": 100663296,
"records": [
{
"name": "model.layers.47.feed_forward.gate_up_proj.q_weight",
"shape": [
32768,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 100663296,
"byteOffset": 0
}
],
"md5sum": "de22eb28ca84a24c4c00f94cbd2a6440"
},
{
"dataPath": "params_shard_238.bin",
"format": "raw-shard",
"nbytes": 24403968,
"records": [
{
"name": "model.layers.46.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.46.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.46.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.layers.47.attention.wo.q_scale",
"shape": [
6144,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2359296,
"byteOffset": 18886656
},
{
"name": "model.layers.47.attention.wqkv.q_scale",
"shape": [
8192,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 3145728,
"byteOffset": 21245952
},
{
"name": "model.layers.47.attention_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 24391680
}
],
"md5sum": "641f2888aa1d9ea5626656dd0fd7f957"
},
{
"dataPath": "params_shard_239.bin",
"format": "raw-shard",
"nbytes": 50331648,
"records": [
{
"name": "model.layers.47.feed_forward.w2.q_weight",
"shape": [
6144,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 50331648,
"byteOffset": 0
}
],
"md5sum": "4d8b731f9e9505ec082f59f37f594e19"
},
{
"dataPath": "params_shard_240.bin",
"format": "raw-shard",
"nbytes": 284295168,
"records": [
{
"name": "output.q_weight",
"shape": [
92544,
768
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 284295168,
"byteOffset": 0
}
],
"md5sum": "d30f9fe98d213ebed349055a203f27fa"
},
{
"dataPath": "params_shard_241.bin",
"format": "raw-shard",
"nbytes": 35536896,
"records": [
{
"name": "output.q_scale",
"shape": [
92544,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 35536896,
"byteOffset": 0
}
],
"md5sum": "ee3e0373996e5f8361443ebfc937e79e"
},
{
"dataPath": "params_shard_242.bin",
"format": "raw-shard",
"nbytes": 18898944,
"records": [
{
"name": "model.layers.47.feed_forward.gate_up_proj.q_scale",
"shape": [
32768,
192
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.47.feed_forward.w2.q_scale",
"shape": [
6144,
512
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 6291456,
"byteOffset": 12582912
},
{
"name": "model.layers.47.ffn_norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18874368
},
{
"name": "model.norm.weight",
"shape": [
6144
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 12288,
"byteOffset": 18886656
}
],
"md5sum": "fb90ffc3790a2dcfd1d93382925673d3"
}
]
}