scigemma_fine_tuned_quantized_MLC / ndarray-cache.json
Hakatoma's picture
Fine-tuned quantized Gemma 2b-it model.
3640b4e verified
{
"metadata": {
"ParamSize": 183,
"ParamBytes": 1409830912.0,
"BitsPerParam": 4.500347711112945
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 262144000,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
256000,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 262144000,
"byteOffset": 0
}
],
"md5sum": "4500be88779baf43abfc8597bf8cf1fe"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "2c18c7025580ced19f7e0145231a4bb8"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 32772096,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
256000,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 32768000,
"byteOffset": 0
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32768000
}
],
"md5sum": "f379b208c95b8217c994896c7b6f2498"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "be970fb1e4887c55ce46223589d373c2"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "eac2c8461a5470cbe5934f49cea50bae"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 30482432,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 2097152
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 6291456
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 6295552
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 8916992
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 9244672
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 11341824
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 11603968
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 11608064
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28385280
}
],
"md5sum": "f9b7ec190e252203052d0ff52e738214"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "47dbbff6a5bf2f946f5514e0a5c4cacc"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 32583680,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 0
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 4194304
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 4198400
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 6819840
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7147520
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9244672
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9506816
},
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9510912
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28385280
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32579584
}
],
"md5sum": "0d0ca39065cab6a21732f487901a395f"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "0400cd4cc8a87fc552b2e18929912104"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 33431552,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 24186880
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28381184
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 28385280
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 31006720
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 31334400
}
],
"md5sum": "ce8ef21c9d6a731962d27f50d1f0fae0"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "bd530edf35ffe58448da5468007e8978"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "8f4b446aad4a9d7130940693fa5e079e"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "4fdd591f3a377f8aa4d4a2cc46a51889"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 30748672,
"records": [
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 0
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 262144
},
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 266240
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17043456
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 19140608
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23334912
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 23339008
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 25960448
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 28385280
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28647424
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28651520
}
],
"md5sum": "e6c11439751edd164e57338d495bf766"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "21cd69165ac6d7fff7328be2bd8a0942"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 32583680,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 0
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 4194304
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 4198400
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 6819840
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7147520
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9244672
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9506816
},
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9510912
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28385280
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32579584
}
],
"md5sum": "a5eee01edf1024d0e03eedee2eb3d301"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "257ff8411113e62b68c3a61c4ff4a6f7"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 33431552,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 24186880
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28381184
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 28385280
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 31006720
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 31334400
}
],
"md5sum": "1b730db433240152f2c0af564dd97f86"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "d215b3a10446bd3e17e5366344581906"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "706a74a4dc6b1066c89c305af1c5b630"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 32841728,
"records": [
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 0
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 262144
},
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 266240
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17043456
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 19140608
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23334912
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 23339008
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 25960448
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 28385280
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28647424
}
],
"md5sum": "a596f0fbe7afcf9882a328f4794918b9"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "8c9dd93c502c85147a805c34f6577243"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 33431552,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 24186880
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28381184
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 28385280
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 31006720
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 31334400
}
],
"md5sum": "d1491e59a4b92d96577b84c952446150"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "3368bfc0cb3fec1f9b6504015249eacd"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "2538ba247784df89f3522ee3360a694c"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "5336205f7dfec13eea071283bf703942"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 30748672,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 0
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 262144
},
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 266240
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17043456
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 19140608
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23334912
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 23339008
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 25960448
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 28385280
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28647424
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28651520
}
],
"md5sum": "e2ae4e7e13d30a8a492e022ef4c81c1f"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "b4aef5bd06260d06c08d9c3e7caa6c56"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 32583680,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 0
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 4194304
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 4198400
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 6819840
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7147520
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9244672
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9506816
},
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9510912
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28385280
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32579584
}
],
"md5sum": "0c0c09fc06d2db1de8ca383d162ff911"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "f59b51e792d09e2dbb5269ecc2769b32"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 33431552,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 24186880
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28381184
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 28385280
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 31006720
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 31334400
}
],
"md5sum": "fcb98fded0d77e12fc1805baad93a6c4"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "9da9e7f1206ea033b5beaaf2a1833b29"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 16777216,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 0
}
],
"md5sum": "6493deac8360ddb78e406cc86775c029"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "07de2046420df60ae1319f2e54683c79"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 30748672,
"records": [
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 0
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 262144
},
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 266240
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 17043456
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 19140608
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 23334912
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 23339008
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 25960448
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 28385280
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 28647424
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 28651520
}
],
"md5sum": "fec04859c07d7573f47ace75b9f44a5a"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 33554432,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
32768,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 33554432,
"byteOffset": 0
}
],
"md5sum": "050839bf4323b2fc55c1d5989d90e32f"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 32583680,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 0
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 4194304
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 4198400
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 6819840
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 7147520
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 9244672
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 9506816
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 9510912
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 26288128
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
32768,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4194304,
"byteOffset": 28385280
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 32579584
}
],
"md5sum": "b79bafb5e0b6fb90e40b0e06d0f35297"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 24195072,
"records": [
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
2560,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2621440,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
2560,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 327680,
"byteOffset": 2621440
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
2048,
256
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 2949120
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
2048,
64
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144,
"byteOffset": 5046272
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 5308416
},
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
2048,
2048
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 16777216,
"byteOffset": 5312512
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
2048,
512
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2097152,
"byteOffset": 22089728
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 24186880
},
{
"name": "model.norm.weight",
"shape": [
2048
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4096,
"byteOffset": 24190976
}
],
"md5sum": "d5547c859d0a1a6f5a981d25568c9c72"
}
]
}