Hugging Face's logo

smalinin
/
Qwen2.5-14B-Instruct_q4f32_1-MLC

Text Generation
MLC-LLM
chat
web-llm
function calling
conversational
Model card Files
xet
Community
1
Qwen2.5-14B-Instruct_q4f32_1-MLC / ndarray-cache.json
smalinin's picture
smalinin
Add model files
3bc4bd5
raw
history blame
246 kB
 {
"metadata": {
"ParamSize": 533,
"ParamBytes": 9234108416.0,
"BitsPerParam": 5.001536828453907
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 389283840,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
152064,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 389283840,
"byteOffset": 0
}
],
"md5sum": "f9768a24e4a722f38640a74f498dcebd"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 48660480,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
152064,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 48660480,
"byteOffset": 0
}
],
"md5sum": "323bf7391cc68a49f27fdd5d9eef22d0"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.47.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "e198568a9d3a27d6da97b6429bd0a561"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 389283840,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
152064,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 389283840,
"byteOffset": 0
}
],
"md5sum": "8a7377bb7925142101656cf1b73c8500"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 48660480,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
152064,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 48660480,
"byteOffset": 0
}
],
"md5sum": "75bca7695c154208d8571ec9d60f7d3b"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "ba08f4bd09086a9a601a6a17d914c993"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "da844c5104df6e70cdacb8ab052f4a75"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.0.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "5259abbf356e362b96be207e9affa335"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 33140736,
"records": [
{
"name": "model.layers.47.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 0
},
{
"name": "model.norm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 4423680
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 4433920
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 4444160
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 8867840
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 17715200
},
{
"name": "model.layers.0.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 17725440
},
{
"name": "model.layers.0.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 17739776
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 20033536
}
],
"md5sum": "b320ccd176c0d57d1a855b4cb8a57311"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "584b75b6c0fc757f3ef926e40676fda6"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "54c270e5389b1ee53a30cc9e280fbde0"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 33294336,
"records": [
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 0
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 1638400
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 1648640
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 6072320
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14919680
},
{
"name": "model.layers.1.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 14929920
},
{
"name": "model.layers.1.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 14944256
}
],
"md5sum": "c7f653176a529561fd9cf8912c0a45d6"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "3799e831f821dd5d5dd92e96595f98e9"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "0c1e614d9e080f628c1e00be0260f5c8"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.2.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "6993cf2eee65fed3f4afc5b8c0442647"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 32638976,
"records": [
{
"name": "model.layers.1.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 2293760
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 15400960
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 17039360
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 17049600
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 21473280
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 30320640
},
{
"name": "model.layers.2.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 30330880
},
{
"name": "model.layers.2.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 30345216
}
],
"md5sum": "256154506d4752147dc1dd6afdbcbce2"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "9d591dfb59177b725c6ae3f30887a14e"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "0c32ea105d34e5a36d1e7fcadff2a485"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.3.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "3cf350049f0dde5bb5a69be745eb67c9"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.3.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.3.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "0f30295482fce73020f954b92f679c17"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 33130496,
"records": [
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.4.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 14766080
},
{
"name": "model.layers.4.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 14780416
}
],
"md5sum": "e086bdad02a2612cfc5f978de2bba6a8"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "e95c246c75ee60b41e24180fb08f282e"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "00c12953ee474de381b03916002c4457"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.10.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "cc63f537090602dfdc2a5c544274d19b"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 32638976,
"records": [
{
"name": "model.layers.4.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 2293760
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 15400960
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 17039360
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 17049600
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 21473280
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 30320640
},
{
"name": "model.layers.10.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 30330880
},
{
"name": "model.layers.10.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 30345216
}
],
"md5sum": "f7d72e750a0b413077a4f95594755efd"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "806583bdcf527ca98dd7f629e3f1bea4"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.11.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "3ad7a2afbcd0305dbc262e47ff6f2dd2"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 25921536,
"records": [
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 14755840
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 23603200
},
{
"name": "model.layers.11.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 23613440
},
{
"name": "model.layers.11.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 23627776
}
],
"md5sum": "1d3c435b1b3dfde86d7f8976d32da7a2"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "de81351a62f072816515faef9c140443"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "bc4d25f2f8c59ed58aba737306aa3bc7"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "d34a119b620e8156b1dab07174a72a86"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "53f2dc6605e4df9e4ed7ff2d597b67f2"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 32450560,
"records": [
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14745600
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19169280
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28016640
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 28026880
}
],
"md5sum": "a181130d296b14821ac369c02da5966d"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 29515776,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 0
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 8847360
},
{
"name": "model.layers.5.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 8857600
},
{
"name": "model.layers.5.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 8871936
},
{
"name": "model.layers.5.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 27222016
}
],
"md5sum": "7c08ff2084d7c4032e2cc1d467a62935"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "b19ff4a5c180e2c9ffcfc383d7a54b5c"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "93558c3a1bea17312cf211212c54665b"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.6.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "884874c458d0e2feec8bd5b72a36d713"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.6.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.6.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "e06b65be87e2dbfca62e5ea53daf3c7c"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "b0e328e4be010db306afe2a0c8482141"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "f7d735872406627ee440b877eb17f723"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.7.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "7a6797ac5e7b32b42bb89199e47734c6"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.7.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.7.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "d9951347153017ed8906a53fd09fea0a"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "ea7ac461948b1ffc413ad556ffd690dc"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "3a8a88e4de8e3a1bec1bcd087b219c86"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.8.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "6fba3c25cec8069ecf6188f797090ce5"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.8.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.8.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "b1a7e78d4a15e89933293bfeff134631"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "d1c94a14fe4c3944b62ad110118eff17"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "a2417e5070c0d5e6eff1074aca908c4e"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.9.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "ad8b4cc116f9320e110d0658f935d885"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.9.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.9.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "57aa9af6d837ea7bc0f26980e1513f43"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "80e55d1d100e98aec101187433447967"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "f479db0a3dd28955d01fcba10f908a9e"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "d5643a79798a805fe48271a773e04d5b"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.12.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "fb896b1aa57986cf06b9af66502fdb3b"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 32475136,
"records": [
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14745600
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19169280
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 19179520
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 23603200
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 32450560
},
{
"name": "model.layers.12.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 32460800
}
],
"md5sum": "846e80f2f918cd8e7231ad1a44f9983e"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "dc8da07835250216591f5f640f272caf"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "8470b59e5c279cd3475174242724cbc8"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.13.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "ce96d1c61bc166d80a4caeff44cecb3c"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 32638976,
"records": [
{
"name": "model.layers.12.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 2293760
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 15400960
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 17039360
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 17049600
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 21473280
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 30320640
},
{
"name": "model.layers.13.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 30330880
},
{
"name": "model.layers.13.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 30345216
}
],
"md5sum": "d48034c42fdfbda3631fff198793fa11"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "ebf81d81b0461f6e58664503ea2957fc"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "649be8d8d2577624ed34b5e122bf22e8"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.14.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "2b267efcda020e2672e3a9321a3efe93"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.14.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.14.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "62f793a9f380d08095c7bd86242548bf"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "054f52cdcf026bbe26077d98dc89e913"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "9148a2d8acb400d9023c355bda42a044"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.15.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "b58743bdfb09d259f77199841c039e05"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.15.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.15.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "47c3edd7b56bad2613ff8a59cc951bac"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "ec3bd2fce92b3746d89a5566d6a034c0"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "c70602cb0b4ea30fd904d19c72c82d8e"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.16.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "4bb9762ba72845d2893ecb0bb54c7a0d"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.16.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.16.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "bd864d786f2f60194eaaf259e4a7dd97"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "c3ff6e091b24b3c5d5359e220142ac10"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "77dcc854771accd34aa3946d30fa6db4"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.17.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "5b3a4964768a29b7e66ab52c00abbf56"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.17.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.17.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "e6d583cbca5494cf96dff2bc14d49e68"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "728af016f9028d1febc83c2a10391ca9"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.18.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "4f979fc81dae288f88cc30f99af7d975"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 25921536,
"records": [
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 14755840
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 23603200
},
{
"name": "model.layers.18.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 23613440
},
{
"name": "model.layers.18.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 23627776
}
],
"md5sum": "9e5c0a93f481eebdd2a9e99dbb80c5a1"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "384124474bbc7d6cb73603834a12ad32"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "1fd5ebdcececa248445411d50a9e4908"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "914255bd599f6fbf98fa59e63fe5ee7c"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.19.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "264294679821a113495cca81b56cad22"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 32475136,
"records": [
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14745600
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19169280
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 19179520
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 23603200
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 32450560
},
{
"name": "model.layers.19.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 32460800
}
],
"md5sum": "29a8a52ed1b2d5de2b31dfa1922eee01"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "91b2576d8a6aa9c422fb4679b2a34e66"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "61eafb5f2e6e998d6f7c905d8d8f5665"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.20.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "4b0c00f7e960f530987770d9426cf923"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 32638976,
"records": [
{
"name": "model.layers.19.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 2293760
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 15400960
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 17039360
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 17049600
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 21473280
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 30320640
},
{
"name": "model.layers.20.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 30330880
},
{
"name": "model.layers.20.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 30345216
}
],
"md5sum": "34b1d91ddec8db836a4165728653c305"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "1fe311440380f5e938073ca6eb492d46"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "ee9b2129231dd72b5676b2e84543b3a6"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.21.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "20fabea46a72871138cf76e080365c3c"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.21.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.21.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "24bdc31cf22da91d62fc1647b4d9d7d4"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "124df224c3637e45f3ab147d37758904"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "3cb26f84946fdaea8982a8d071048588"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.22.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "5dee9bf53a7557cfeabe0e0db7bc6c7a"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.22.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.22.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "5ce84d0e7d121435ba91b73f81da38c9"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "d17d346afe41b1516a90493a69c729e5"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "188fef352dd53f3100d9b1675dc72421"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.23.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "a22fd42b5bc407657351329edfd6d243"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.23.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.23.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "2c9bd48c7887009edda079bed943c5e6"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "c14fbff5cecc8f69754f059dbfafa31b"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "bdc3c4ea5bc0c9f21dfd8a19e8ddf763"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.24.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "8686453ea86d1dc2a655cb0a5a046f43"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.24.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.24.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "bba0196de43bd56897f5fcd82ba8a4f0"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "ad7460392a5502f909384c19d9fb498c"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "a8b795c6d9e84d75e557d2d6f57bbbbb"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.25.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "39ff47c0e32e461ce6d92a9326e5d04a"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.25.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.25.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "a0ad807cde27e8474eaf31157d216e46"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "23a85c7a8484fddd0e4d585fbabf17d1"
},
{
"dataPath": "params_shard_108.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "e6685b036bc43cfdf43845e2097cce8c"
},
{
"dataPath": "params_shard_109.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.26.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "911f9cd69713ae6b08f2595d8323d1ca"
},
{
"dataPath": "params_shard_110.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.26.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.26.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "7e9ff4f6b18655c79673cb8d7185c507"
},
{
"dataPath": "params_shard_111.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "df631d8c2b95161985ff71a0a6cb803b"
},
{
"dataPath": "params_shard_112.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "d27ece2150651ae07d8dd75ffc3e093d"
},
{
"dataPath": "params_shard_113.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.27.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "9a36772453581e2fc3bb4fa70dd4becd"
},
{
"dataPath": "params_shard_114.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.27.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.27.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "20a478bedeab2c57acbe19b2ed2fd7e3"
},
{
"dataPath": "params_shard_115.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "e9bc0ed79a9cab5e55d2922ee6d9d042"
},
{
"dataPath": "params_shard_116.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "c12aaaab38142f8052e2da0092719d19"
},
{
"dataPath": "params_shard_117.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.28.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "edff050a90b1801da3a203c933c23d81"
},
{
"dataPath": "params_shard_118.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.28.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.28.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "933930cdf69010b0adf4a8c0bc29ddbe"
},
{
"dataPath": "params_shard_119.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "036b12f0c0e85360c127bb3be49df422"
},
{
"dataPath": "params_shard_120.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "2a796a270f11a1de254efd2a04d8e66d"
},
{
"dataPath": "params_shard_121.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.29.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "7f5c62d4ccde092fcbee6073666c8fa5"
},
{
"dataPath": "params_shard_122.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.29.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.29.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "a3c7d0a19c62ee1399723c8e69d02378"
},
{
"dataPath": "params_shard_123.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "09bdc39b496241e7d7e8086bf2f16795"
},
{
"dataPath": "params_shard_124.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "881ff0be7269ae8c4d840f9506dc1f9f"
},
{
"dataPath": "params_shard_125.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.30.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "462733aec09c23d6e68efff2a93d27db"
},
{
"dataPath": "params_shard_126.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.30.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.30.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "552129fa9ada776916e73b792696cafe"
},
{
"dataPath": "params_shard_127.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "ba707e583e9e890573b26f97cd3be5c2"
},
{
"dataPath": "params_shard_128.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "5fc70c481672ba2da9df1557b6fc3db2"
},
{
"dataPath": "params_shard_129.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.31.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "a035d445e3e335d49aaff7150207c4da"
},
{
"dataPath": "params_shard_130.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.31.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.31.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "a0891fd52cc5332d1e7f480b2474644d"
},
{
"dataPath": "params_shard_131.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.32.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "87f3d850d759d8524ed53e9610c2e750"
},
{
"dataPath": "params_shard_132.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.32.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "0396529a75f847b844ad4c866c130130"
},
{
"dataPath": "params_shard_133.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.32.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "f170140cb785d9e3c75d93509bd5fc28"
},
{
"dataPath": "params_shard_134.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.32.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.32.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.32.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.32.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.32.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.32.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "3cd07f35c39295caed41831a516de9b8"
},
{
"dataPath": "params_shard_135.bin",
"format": "raw-shard",
"nbytes": 33130496,
"records": [
{
"name": "model.layers.32.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.32.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.33.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.33.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14755840
},
{
"name": "model.layers.33.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 14766080
},
{
"name": "model.layers.33.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 14780416
}
],
"md5sum": "2a44df0631f9a11a246e3dd88cf413f0"
},
{
"dataPath": "params_shard_136.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.33.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "e96841b8f2a7aea8adf7659c5b27f3be"
},
{
"dataPath": "params_shard_137.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.33.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "1a0a5c77b2224e5e28787b4525836a97"
},
{
"dataPath": "params_shard_138.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.34.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "dafcbc97752a7726cdc7113d229dc83a"
},
{
"dataPath": "params_shard_139.bin",
"format": "raw-shard",
"nbytes": 30320640,
"records": [
{
"name": "model.layers.33.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 0
},
{
"name": "model.layers.33.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 2293760
},
{
"name": "model.layers.33.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 15400960
},
{
"name": "model.layers.33.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 17039360
},
{
"name": "model.layers.33.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 21463040
},
{
"name": "model.layers.34.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 30310400
}
],
"md5sum": "f0dc3c03db418324190510b0b8816f3e"
},
{
"dataPath": "params_shard_140.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.34.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "e77bd98dfc13a3a0fac2d0d59350ed53"
},
{
"dataPath": "params_shard_141.bin",
"format": "raw-shard",
"nbytes": 31645696,
"records": [
{
"name": "model.layers.34.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 0
},
{
"name": "model.layers.34.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 4423680
},
{
"name": "model.layers.34.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 13271040
},
{
"name": "model.layers.34.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 13281280
},
{
"name": "model.layers.34.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 13295616
}
],
"md5sum": "c7cb3f9a243fc5934b1467d4b1fc2e04"
},
{
"dataPath": "params_shard_142.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.35.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "9eb81ffc0536705e70d3e9b75dff4ebf"
},
{
"dataPath": "params_shard_143.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.35.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "b45cb9ca71300bb12ec9a3378968e4ec"
},
{
"dataPath": "params_shard_144.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.35.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "9f48626718058c03d9334d3a952912e1"
},
{
"dataPath": "params_shard_145.bin",
"format": "raw-shard",
"nbytes": 32638976,
"records": [
{
"name": "model.layers.34.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 0
},
{
"name": "model.layers.34.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 2293760
},
{
"name": "model.layers.34.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 15400960
},
{
"name": "model.layers.35.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 17039360
},
{
"name": "model.layers.35.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 17049600
},
{
"name": "model.layers.35.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 21473280
},
{
"name": "model.layers.35.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 30320640
},
{
"name": "model.layers.35.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 30330880
},
{
"name": "model.layers.35.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 30345216
}
],
"md5sum": "39483915cb04eae15a6a12949e328f47"
},
{
"dataPath": "params_shard_146.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.36.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "314e99ac14dcb08cc75a62ce9eae660a"
},
{
"dataPath": "params_shard_147.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.36.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "105e5e7cbb5b439694aaea1172aed5c6"
},
{
"dataPath": "params_shard_148.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.36.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "dd9cf79b5e5c8778f0f4f9dbeadca213"
},
{
"dataPath": "params_shard_149.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.35.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.35.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.36.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.36.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.36.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.36.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.36.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.36.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "34acb0a4db44871b7133f821ae0a51b1"
},
{
"dataPath": "params_shard_150.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.37.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "b66a6ba4dc75bf2036be00b2e6991a31"
},
{
"dataPath": "params_shard_151.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.37.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "a230b6eeb20ed67b09beea4dd118c996"
},
{
"dataPath": "params_shard_152.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.37.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "fe333711d1b0360a28fbeb9dd5fb6433"
},
{
"dataPath": "params_shard_153.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.36.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.36.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.37.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.37.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.37.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.37.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.37.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.37.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "1332f9f7b1f74670eee566b6dc2a5e9d"
},
{
"dataPath": "params_shard_154.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.38.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "0dbe1747af263a179076ef2dd12297c9"
},
{
"dataPath": "params_shard_155.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.38.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "5d4e18b1656d371a5d5ca53a33772896"
},
{
"dataPath": "params_shard_156.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.38.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "662a65541920d193417508baf4baedac"
},
{
"dataPath": "params_shard_157.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.37.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.37.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.38.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.38.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.38.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.38.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.38.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.38.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "965e6ccb03493229655f81dc8addf6e5"
},
{
"dataPath": "params_shard_158.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.39.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "97a0397b1a1db03f02a6383a3d249226"
},
{
"dataPath": "params_shard_159.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.39.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "fd80d91d8fdf90b63d711b9de5a8f195"
},
{
"dataPath": "params_shard_160.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.39.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "697cbd823f20ca083959d44981e70436"
},
{
"dataPath": "params_shard_161.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.38.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.38.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.39.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.39.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.39.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.39.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.39.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.39.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "39a886bea6b8aee6c96ef05710eaa697"
},
{
"dataPath": "params_shard_162.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.40.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "a86bd84b53fe38fbb9f3ceae56f1ee3a"
},
{
"dataPath": "params_shard_163.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.40.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "947460a9f959255452cd9c5f48a6d217"
},
{
"dataPath": "params_shard_164.bin",
"format": "raw-shard",
"nbytes": 25921536,
"records": [
{
"name": "model.layers.39.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.39.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.40.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.40.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 14755840
},
{
"name": "model.layers.40.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 23603200
},
{
"name": "model.layers.40.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 23613440
},
{
"name": "model.layers.40.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 23627776
}
],
"md5sum": "a0b93f128812949f65b2a5f7139c7b79"
},
{
"dataPath": "params_shard_165.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.40.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "baf63e9e728051ebbcc134bd0cff4602"
},
{
"dataPath": "params_shard_166.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.41.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "687f738ea1e36081c78192ce9910b1bc"
},
{
"dataPath": "params_shard_167.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.41.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "df07929ebe62610acb7671559858084e"
},
{
"dataPath": "params_shard_168.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.41.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "9c16eebab302b6d212913720e848615a"
},
{
"dataPath": "params_shard_169.bin",
"format": "raw-shard",
"nbytes": 32475136,
"records": [
{
"name": "model.layers.40.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.40.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.40.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14745600
},
{
"name": "model.layers.41.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 19169280
},
{
"name": "model.layers.41.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 19179520
},
{
"name": "model.layers.41.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 23603200
},
{
"name": "model.layers.41.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 32450560
},
{
"name": "model.layers.41.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 32460800
}
],
"md5sum": "f6910fd5e187f01234dab7c8bf6934b1"
},
{
"dataPath": "params_shard_170.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.42.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "156d272c5095c5420a6ff20965ba1301"
},
{
"dataPath": "params_shard_171.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.42.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "4a24ef0bbe21a509ee1f1433dbd4c42c"
},
{
"dataPath": "params_shard_172.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.42.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "46ad6bf95fe52e9d072b493a382029a9"
},
{
"dataPath": "params_shard_173.bin",
"format": "raw-shard",
"nbytes": 32638976,
"records": [
{
"name": "model.layers.41.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 0
},
{
"name": "model.layers.41.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 2293760
},
{
"name": "model.layers.41.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 15400960
},
{
"name": "model.layers.42.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 17039360
},
{
"name": "model.layers.42.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 17049600
},
{
"name": "model.layers.42.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 21473280
},
{
"name": "model.layers.42.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 30320640
},
{
"name": "model.layers.42.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 30330880
},
{
"name": "model.layers.42.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 30345216
}
],
"md5sum": "b293df1b7e5bd1c8a7bccf8857ceeb35"
},
{
"dataPath": "params_shard_174.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.43.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "62ad85befd9fe921b6bef8e32582e3b1"
},
{
"dataPath": "params_shard_175.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.43.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "4edb1d31cbe9cbc1726ea1a4984089b8"
},
{
"dataPath": "params_shard_176.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.43.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "69d97d0641a5963a2630a2160a795dc3"
},
{
"dataPath": "params_shard_177.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.42.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.42.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.43.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.43.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.43.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.43.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.43.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.43.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "ee5f5c85b83ea4c31d277affa8cd49a8"
},
{
"dataPath": "params_shard_178.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.44.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "eecbd75232b5d9925e17d71ad3aa736b"
},
{
"dataPath": "params_shard_179.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.44.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "0fa2814172f74267e10e3c121bbc0c66"
},
{
"dataPath": "params_shard_180.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.44.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "d8f3050f9f84aa60c7160240fbe58104"
},
{
"dataPath": "params_shard_181.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.43.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.43.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.44.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.44.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.44.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.44.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.44.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.44.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "47cde72c80f58d4a091145c438ce9e89"
},
{
"dataPath": "params_shard_182.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.45.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "c75e80933edaa0fd3799274fcdbf860d"
},
{
"dataPath": "params_shard_183.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.45.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "146d3acdcbcb587e82956cf37438f969"
},
{
"dataPath": "params_shard_184.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.45.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "1b067051c1826ecc6abb63a8ea080bb1"
},
{
"dataPath": "params_shard_185.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.44.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.44.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.45.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.45.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.45.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.45.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.45.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.45.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "1b950b0f59d066cf19f5d9f1fcc2e360"
},
{
"dataPath": "params_shard_186.bin",
"format": "raw-shard",
"nbytes": 35389440,
"records": [
{
"name": "model.layers.46.mlp.down_proj.q_weight",
"shape": [
5120,
1728
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 35389440,
"byteOffset": 0
}
],
"md5sum": "387b85d301544976e07ca674e347a566"
},
{
"dataPath": "params_shard_187.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.46.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "baa122c87da2fe0f2b58cb5e2137dec8"
},
{
"dataPath": "params_shard_188.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.46.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "a0f647eac4a908a1ed3aa7d26aeac498"
},
{
"dataPath": "params_shard_189.bin",
"format": "raw-shard",
"nbytes": 30345216,
"records": [
{
"name": "model.layers.45.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.45.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.46.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.46.mlp.down_proj.q_scale",
"shape": [
5120,
432
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 4423680,
"byteOffset": 14755840
},
{
"name": "model.layers.46.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 19179520
},
{
"name": "model.layers.46.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 28026880
},
{
"name": "model.layers.46.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 28037120
},
{
"name": "model.layers.46.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 28051456
}
],
"md5sum": "8d60581ce145c91a491bad493dbd4031"
},
{
"dataPath": "params_shard_190.bin",
"format": "raw-shard",
"nbytes": 70778880,
"records": [
{
"name": "model.layers.47.mlp.gate_up_proj.q_weight",
"shape": [
27648,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 70778880,
"byteOffset": 0
}
],
"md5sum": "591358b94e48758321edc40dc6cfb507"
},
{
"dataPath": "params_shard_191.bin",
"format": "raw-shard",
"nbytes": 18350080,
"records": [
{
"name": "model.layers.47.self_attn.c_attn.q_weight",
"shape": [
7168,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 18350080,
"byteOffset": 0
}
],
"md5sum": "ca99b5589b11801410ad0be08cdbff32"
},
{
"dataPath": "params_shard_192.bin",
"format": "raw-shard",
"nbytes": 25921536,
"records": [
{
"name": "model.layers.46.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.46.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
},
{
"name": "model.layers.47.input_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 14745600
},
{
"name": "model.layers.47.mlp.gate_up_proj.q_scale",
"shape": [
27648,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 8847360,
"byteOffset": 14755840
},
{
"name": "model.layers.47.post_attention_layernorm.weight",
"shape": [
5120
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 10240,
"byteOffset": 23603200
},
{
"name": "model.layers.47.self_attn.c_attn.bias",
"shape": [
7168
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 14336,
"byteOffset": 23613440
},
{
"name": "model.layers.47.self_attn.c_attn.q_scale",
"shape": [
7168,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 2293760,
"byteOffset": 23627776
}
],
"md5sum": "79f139afaab23d4f2fbfdb0a353aafd1"
},
{
"dataPath": "params_shard_193.bin",
"format": "raw-shard",
"nbytes": 14745600,
"records": [
{
"name": "model.layers.47.self_attn.o_proj.q_weight",
"shape": [
5120,
640
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 13107200,
"byteOffset": 0
},
{
"name": "model.layers.47.self_attn.o_proj.q_scale",
"shape": [
5120,
160
],
"dtype": "float32",
"format": "f32-to-bf16",
"nbytes": 1638400,
"byteOffset": 13107200
}
],
"md5sum": "b79ed704c20b8b2e2f518605a75f4eb3"
}
]
}