numen-tech's picture
Add weights
8910fe7
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 3274754296.0,
"BitsPerParam": 2.608942222483959
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 52739296,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
32002,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 52739296,
"byteOffset": 0
}
],
"md5sum": "1fe5cfcbd64a128d0c5a78290c600a1d"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "8635cbbedfbc5901a2b658dde10a5519"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 52739296,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
32002,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 52739296,
"byteOffset": 0
}
],
"md5sum": "567b433d8f1ad3735ca058f6187a3f31"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "fa0a3c51ded04088c00c5dc14acf2e9e"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "12ac14ba7c89da2ad5f674d66581f86f"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 27979576,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
32002,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6592412,
"byteOffset": 0
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 6592412
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 6600604
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12507036
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 12515228
},
{
"name": "model.embed_tokens.q_scale",
"shape": [
32002,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 6592412,
"byteOffset": 12523420
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 19115832
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 19124024
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 22064952
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27971384
}
],
"md5sum": "dd4c7a334169c41499694dc2b3a2d22a"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "67070bde2e58bea03c5f1b7b874446a2"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "f21624eb90ef0b3efc57fc78edbd22c4"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18984960
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 18993152
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 21934080
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
}
],
"md5sum": "3d22939c52fb71ee1d8420bd37aaa5cb"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 30375936,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 18984960
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 29110272
}
],
"md5sum": "0fa22c887b38e3595f28dab27f975fb1"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 31129600,
"records": [
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 6750208
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7593984
},
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 7602176
}
],
"md5sum": "13589dfccb6e4400387c5900b336fb17"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "413a6b3c15c9eee057aa7c28f9040c7c"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "b11f498a2d03c55b3fe9d3b60571b5f6"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "40abec6bc5a11be183948288e752fa3f"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 30789632,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 2940928
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8847360
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 8855552
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 18980864
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 20246528
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 26996736
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27840512
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 27848704
}
],
"md5sum": "f1adcb1961d2f3b304609d3c07ce9fb2"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "5db427ce98253fa89ba207e797fd54ca"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "7dcd43d1406cfe90685d1e8893659848"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "889d2b42add77128972e24bea2047ed6"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "1adb71302d2301a6e9ea11ebdd0c8613"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "d7b41cd5905b2392c160afeef4b3850e"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "a101679e7eb803f6bffd317b178cd006"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "d6b605305e825064eca99ecfcbbf9a7d"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "0838eb8b5cb5a32d26f74be0389f1444"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "76d19cf4cfc78d9e0d9aa1a01bee03bc"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "1ccb44c2cf20f68afd98187128dcf047"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "a749c189160d70931d137203cb2c094f"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "b670783d7f1991d0269f25b13fac5785"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "3d6fa49fbb8fde1435abeefd9c1e68bb"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "230f4ed666f97c5f142daf083dde67ba"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "18ecaa0e12a07c2a2dc044b893b46dd3"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "a9b5e1654faf02a7f7882fde83e14700"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "5339929512465712ecd09d21d80405c2"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "8d822bf7d3d9c2d0d065154c81a7c152"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "a0487801bd4556bfeb7050fab175327b"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "e0ff067ae3043053916d5e63b784ba67"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "55ae829b0814baeebdd40382fd492167"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "47dc62d07f39d6245a6c7bd5c2fe144a"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 32391168,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5914624
},
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 5922816
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 29450240
}
],
"md5sum": "3ca6e32020159449eb083f5070dd1a90"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "acbaa94c09f7d0022a38fa7ff825e498"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "79e1c64e62a4fc1de36741e10c3822fb"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "f3b3eab3d8735045880b5147b6e1b813"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "9224f260a8fd5ea73746cf8ce8739e7b"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "2b650134d7ee6885dd8c8aa55bc55fef"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "31f6a3d35c3a43020c027ddb5ca83695"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "f6f24cf1e9b8d78def936dbfffa27ca2"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "2ea0b1e1ab770f1c24cc07f1d5a08114"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "84751e65f0bb3ecc6b77aaad7165875d"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "9fdbb2acd97b194df1d024e96f66d5b8"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "c73dec758cc4b37cd4f48f17f4d4b4ab"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "3a7062caf7d107153ca103b1e5b91cb7"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "534ee83ce89c2bfd3f62e5fec1877ced"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "047357cef260bc3fbe9a1c70a36ae5e7"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "4d528fd399dd45c92f33e13852a80f0c"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "590db55586734f1805b5c579f7383a0c"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "4fb8559d269f437b77d02abae46ae1d9"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "4fc939397b3af9183603b31c5319b719"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "53744ad029487cc4390be7958ca3c0cd"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "bea69606fa14f183cae3143740fb7a88"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "d5ad28f3584af626d8034a6274f6a56e"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "b2dfa2abb58a4bafdae3c67608a88698"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "dc57e37ce0bee26baf15519e02b79747"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "6ddc99544bffd2830bfd764fa6f6b93e"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "8d36c5ed9959dcba7b6edd25ec433d7c"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "3d464b302c287ab391df914cb1ef6bd5"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "f24330ffaea6de1db9c56d06dc5a3b93"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 24899584,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
}
],
"md5sum": "7c3d232359b499661137957fa1ae32ff"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "aa67d56b3b47143785054dde58174b43"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "edbe299446b52ec30902de8ba3cc6b0b"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "f78295dd45e2c1e54ce6ce41870d60ca"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "a877eee65813288a0d1e3442f0068615"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 30797824,
"records": [
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11390976
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 11399168
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 14340096
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20246528
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 20254720
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 27004928
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27848704
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 27856896
}
],
"md5sum": "38c879f2427dd8004b505ff6c4287b0c"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "1e031367f48f2582f2d7fc6ca0b30007"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "71eca53bf2da9570860fc7583c6168c5"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "0c99900d6c54244919e2cd6b6c36a5b6"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "e6dcda4588fc07b0ee16e671b6ae1f6c"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "6442595f798ea842b511828bb6cb0261"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "b76a757c40f952486f548e9148d1b503"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "bb1c30bb383772c448c6b76aca361475"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "1e9a59338bedcffb3c3ef471e6244234"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "83b1517d0233b0b9fbf54e76b38482ef"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "f56eaad4e400c0a1b6e604d1e3ce4b7b"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "61183f257aef18a663d21387e723442f"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "e2a50d2c04dbf764743deb377decbb46"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "137b818c43fd793e6463962a7159464a"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "125be474c056acaff3396410114f652f"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "1ff6ffe9107f0571f1842c0e46b2f346"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "eef6f594bd6c3b9ffdf9aaf6b120bdd2"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "836c000ed2ddda5a4b1ccd81645fa75c"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "6c1a5c7c968422ca1419189f6b97d3e1"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "bb812e766f025b7ceac316bf0efe194c"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "366b78724bfcce38d6db865ad0835e14"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "046901d043cc2a4e7ab6ca2f254a9395"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "31ae286029b39e57d4cd06aa8a59b711"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 47251456,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
28672,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 47251456,
"byteOffset": 0
}
],
"md5sum": "bb75ad9bc98bd174a8d00b61ffb3fd9b"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 27848704,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 24899584
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24907776
}
],
"md5sum": "72ac9e6b2ebba950dcee2d6148fefa94"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 23527424,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
4096,
1436
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 23527424,
"byteOffset": 0
}
],
"md5sum": "1e9bdab719e0418d88fbe497f15f2ffd"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 27840512,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
28672,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 5906432,
"byteOffset": 0
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 5906432
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 5914624
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 16039936
},
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 17305600
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 24055808
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
359
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2940928,
"byteOffset": 24899584
}
],
"md5sum": "4683255ce4ba6b50a89dbccea5a6892e"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 18984960,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
6144,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 10125312,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
6144,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1265664,
"byteOffset": 10125312
},
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
4096,
412
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 6750208,
"byteOffset": 11390976
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
4096,
103
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 843776,
"byteOffset": 18141184
}
],
"md5sum": "7d94412b11059f28d2abfded3d1cef72"
}
]
}