numen-tech's picture
Add weights
4074897
{
"metadata": {
"ParamSize": 507,
"ParamBytes": 4766153728.0,
"BitsPerParam": 4.068522985105678
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 458752000,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
256000,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 458752000,
"byteOffset": 0
}
],
"md5sum": "ffe5f6373041bc63934fc7082a5b99dc"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "6338b917dba5cdf094bb9cea4c043fcf"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "715717a5458b801b262cfc6e41d53702"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 31911936,
"records": [
{
"name": "model.embed_tokens.q_scale",
"shape": [
256000,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 14336000,
"byteOffset": 0
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 14336000
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 14343168
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 15145984
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 16751616
},
{
"name": "model.layers.0.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 16758784
},
{
"name": "model.layers.0.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 16765952
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 16773120
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 31453184
}
],
"md5sum": "7ea8b1ac7c85384cdc20a9422f5ce975"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 33266688,
"records": [
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 7340032
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 7569408
},
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 7576576
}
],
"md5sum": "64e97465dfce788ff82082bb3706be68"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "115edbe78dab8df84d8dfcfa6942f836"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "418b224f006850bd3b1fd3476b083b9d"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "c58861689bebf2ef01f8564316dd237a"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 27575296,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 802816
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2408448
},
{
"name": "model.layers.1.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2415616
},
{
"name": "model.layers.1.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2422784
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 2429952
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 17110016
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 17568768
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 24908800
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
},
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 25145344
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 25948160
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27553792
},
{
"name": "model.layers.2.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27560960
},
{
"name": "model.layers.2.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27568128
}
],
"md5sum": "bf624909c74ffe274963b1e47c3720dc"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "f904de6b52231fcf4afca205c53fb228"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "c6d662221fea44ba57c0b407d053eb61"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.3.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.3.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "ac882abfab8a786bdfd8cb5418f8f612"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "4bfd1b1e48400cd68f6c3ad8de34832e"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "94a173ab6290b066b03f620c1a0fd11d"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.4.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.4.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "6f6c48a6326802956d1dac73dad4b4fa"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "c536eee324be8bec69b89a27f8567130"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "f5cb03a3806ce69d7d44be25723fbcc2"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.5.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.5.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "973038f040fc25e33f9cc5d169a3c7da"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "1e1b4dfc56f88d3cd334cdc6d1fd2bb1"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "fcea4d649a0bd3b8343a7aafcbf93d67"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.6.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.6.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "a26ab18c13d0729c8b3a7f199ef282e1"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "55fa2e00991ef3997a15c9a1584b01da"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 24313856,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 22708224
}
],
"md5sum": "355cc74bb6cddf5de9848bbe606a9611"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "4c9d7d646152dea460e47f2c83d8f071"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "83cd05ebdfc557de177d3d689a902bc3"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.10.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.10.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "711a88bae91c6fdc554585dfe278834b"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "b3b8f45c4e068caa328228b71d5b747d"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "9bfe0a0f59f4df9e7d19b01af266bd1b"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.11.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.11.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "f798a0c7b57aa6baf87680ef148732d0"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "e92772b8001683e503c012441dd22363"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "ab7c4183ccbd1aa925560a5fed444056"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.12.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.12.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "1850bd1f80b29a99b0c48b4dae33f60f"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "c8b5bc4e0afe71757d1ed96acdbfefeb"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "1fb9945853afa063ee163cd8e1e87ba2"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.13.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.13.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "00784137a59b2269a3399079e027d690"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "68c8713ddac09ec9ac2f1c3de1aa6675"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "10d85462fa9ce76884630fc25d14c048"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.14.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.14.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "db46ce60149d943537bde395a1ae14c5"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "8dae1dcc2acd7034cfd05afa26f7e010"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "f534d2ed3ebcd31b2a66b29adb7b1e26"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.15.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.15.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "c61ac394f728e66efb95def6b0370351"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "12c1fbf8ca46138aa74e63b27ca9e0e2"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "aad020af77529e562f0cd841fd4a9e04"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.16.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.16.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "e738b897d8f9d15fdf1030d6d35a8856"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "e49e012f01047e76160f0a0772c8bc98"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "229e979704de96da9250b1485f112de4"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.17.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.17.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "9b64298826e6f8900d3fb198a46c608d"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "c22b5ea6e17dd66a0c016b402c1706f0"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "b57846a637816f903297d6f4c8f0ac40"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.18.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.18.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "26b41ae85f299f14a907a78309372103"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "de0e14bae6e4677bde08ef64c7bd96f2"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "19dd88ecc35ad23a5f3a27c4b522eca2"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.19.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.19.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "9668f54b3e0691066a6ac04ffb114f7b"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 22708224,
"records": [
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
}
],
"md5sum": "ece8a0143c805d22b506b7ae8d073a43"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "21302fd7694c65f621acd1b94600fae4"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "ead3dcd28f6ede74397094f205a175cd"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "5dc99fa865d4387f21ea96fa7dfd275b"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 33546240,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 15138816
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 15145984
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 15948800
},
{
"name": "model.layers.7.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 15955968
},
{
"name": "model.layers.7.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 15963136
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 15970304
},
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 15977472
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 16780288
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 18385920
},
{
"name": "model.layers.8.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 18393088
},
{
"name": "model.layers.8.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 18400256
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 18407424
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 33087488
}
],
"md5sum": "bd23ec8d643520050ad4db15d003b705"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 33266688,
"records": [
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 7340032
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 7569408
},
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 7576576
}
],
"md5sum": "0b2203f2ad10c64e305f17039e484c1a"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "99543324e01d636af4da6f2cdc8b8829"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "c949e5e7a2e58b1e0662f4014b112e82"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "736c7e370fa1e84ce7cf59bde1725fda"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 27575296,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 802816
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2408448
},
{
"name": "model.layers.9.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2415616
},
{
"name": "model.layers.9.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2422784
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 2429952
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 17110016
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 17568768
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 24908800
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 25145344
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 25948160
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27553792
},
{
"name": "model.layers.20.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27560960
},
{
"name": "model.layers.20.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27568128
}
],
"md5sum": "9d2fe7ce4153c03e0dbee9ae638c469f"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 33266688,
"records": [
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 7340032
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 7569408
},
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 7576576
}
],
"md5sum": "8150c608bbb06ecc6444d277a56bd50b"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "d62045e9983cff07076c6beb21c6c566"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "716f425da6420e63e132f56aa11cb1c0"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "664b44ab0e187fa136d8940dec1ac5a2"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 27575296,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 802816
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2408448
},
{
"name": "model.layers.21.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2415616
},
{
"name": "model.layers.21.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 2422784
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 2429952
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 17110016
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 17568768
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 24908800
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 25145344
},
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 25948160
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27553792
},
{
"name": "model.layers.22.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27560960
},
{
"name": "model.layers.22.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 27568128
}
],
"md5sum": "81e64d16c630f51dc652593baf54f8c3"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "5343fbc392b497d304fb8410d714a630"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "16ee25ce525deed4b3e1d7e919b262a8"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.23.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.23.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "b09b65ae0f6bbbb18b3b1023267c7720"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "c8c49a748eecf8db45106ad330838045"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "09dfa6eb4dd6f6c97575cd6b6b5606cf"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.24.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.24.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "3403a09cf526d18bd513a4439d6582a2"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "4592e9fb477c910955a5fbda5242d3ed"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "f57c17822bde9e6390d69759cd1736e3"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.25.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.25.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "f9e06c3c70fc0a085a32669223beddc9"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "0a0ba3f6a02669e3c9bc6013f3ac4c32"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "f56d312142bd97635f1fa0ae3f17f15b"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.26.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.26.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "c32f3caf3f8730be02ffec6feb66b9de"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "792992668d921df222c4d52c1d1dd91f"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "00b7dbc8785fc142453d1237fdeabae2"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.27.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.27.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "195770a88d930497d04cbccb9023bcc5"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "118867ccf21e3db47d5e609744749e0c"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "9ca856c9403473291d79c2ba0854948a"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.28.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.28.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "5fac976afdf905f5052e7e65f06925b9"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "46cfa18f396e42346128373d9781e6bb"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "230b2bfea8e43be43f1d84ffacb4369e"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.29.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.29.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "0dfe69058c8f4ca265b0163fc87ab82d"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "e8bb76ee7bcf08273da8d8a3d9e38064"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "5fe917bb4469db9faa5b247f033a23c8"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.30.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.30.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "b2bbf0e774446881863e3ed3faa17691"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "5771cd2f0d1e9297da5b408fb1198498"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "6ce0df95427a1bed1d584c8d804bb190"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.31.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.31.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "50470d652bec70ba048c9418021bb5cb"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.32.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "9a3c92e9035db214e47ee5ebbd406e60"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 24313856,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.32.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 22708224
}
],
"md5sum": "87a92bdab59c6a0d0bc51580beff0851"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.32.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "59780d02b50340a6080a80ae1c64428d"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.33.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "d66e7f4f56353d75ba23258d2273152b"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.33.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "6cb702cd6a80e52ed26e0a1bdfbe20ce"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 25976832,
"records": [
{
"name": "model.layers.32.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.32.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.32.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.32.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.32.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.32.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.32.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 23518208
},
{
"name": "model.layers.32.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 23525376
},
{
"name": "model.layers.32.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 23532544
},
{
"name": "model.layers.33.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 23539712
},
{
"name": "model.layers.33.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 23546880
},
{
"name": "model.layers.33.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 24349696
},
{
"name": "model.layers.33.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25955328
},
{
"name": "model.layers.33.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25962496
},
{
"name": "model.layers.33.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25969664
}
],
"md5sum": "6d467f4d30cdeda41887888eb1db34b3"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.34.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "ceffd375b505e120818cb76d8ae7da0c"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.34.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "78de75e8f4fdbb245cb24b8022539508"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.33.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.33.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.33.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.33.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.34.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.34.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.34.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.34.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.34.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.34.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "1fc1aa2b4cad069bcd5b9d5ae862e2ba"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.35.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "d752e6bfd516184e28e7afac7820062f"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.35.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "5a9ab7960f2c708ff2eb8df00ef43f79"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.34.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.34.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.34.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.34.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.35.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.35.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.35.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.35.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.35.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.35.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "dbf33f4933bca53456cae2fc39c119c9"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.36.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "84883d396c86db375b33e0db68abe4ba"
},
{
"dataPath": "params_shard_108.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.36.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "91d4acac94770677b67b5e36f51cad66"
},
{
"dataPath": "params_shard_109.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.35.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.35.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.35.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.35.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.36.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.36.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.36.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.36.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.36.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.36.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "956ea7d62e13e10d1fac4925e32afac9"
},
{
"dataPath": "params_shard_110.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.37.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "7f9ff56706d9a086236bc2c1d0c3954c"
},
{
"dataPath": "params_shard_111.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.37.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "1570a453d816fa8555212a2a302d6f6b"
},
{
"dataPath": "params_shard_112.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.36.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.36.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.36.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.36.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.37.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.37.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.37.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.37.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.37.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.37.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "7d08aaba8118acf47a1a5dd1c4093d35"
},
{
"dataPath": "params_shard_113.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.38.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "a3bd504422e9880cb2d3a28145e4d626"
},
{
"dataPath": "params_shard_114.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.38.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "41e2b14c432043035f970848de2cb134"
},
{
"dataPath": "params_shard_115.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.37.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.37.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.37.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.37.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.38.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.38.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.38.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.38.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.38.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.38.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "54033655cb9398bb729b63fbe5a314cc"
},
{
"dataPath": "params_shard_116.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.39.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "3dd713f45d2499c14f3e41f01394e8c4"
},
{
"dataPath": "params_shard_117.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.39.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "15093b9730ac31f60cc14eb9219b9f83"
},
{
"dataPath": "params_shard_118.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.38.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.38.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.38.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.38.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.39.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.39.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.39.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.39.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.39.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.39.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "de1cce49770cc934772f9a8425c7be91"
},
{
"dataPath": "params_shard_119.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.40.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "93f9933d165b9669faf402c5275ac8c8"
},
{
"dataPath": "params_shard_120.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.40.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "bb543e194c1c6a59854ea736b7acfa3e"
},
{
"dataPath": "params_shard_121.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.39.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.39.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.39.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.39.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.40.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.40.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.40.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.40.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.40.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.40.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "5f72d3bf2c852c1721b5c5d8b6679588"
},
{
"dataPath": "params_shard_122.bin",
"format": "raw-shard",
"nbytes": 25690112,
"records": [
{
"name": "model.layers.41.mlp.down_proj.q_weight",
"shape": [
3584,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 25690112,
"byteOffset": 0
}
],
"md5sum": "dbc98b5d2845b7e2e86de865c010e04e"
},
{
"dataPath": "params_shard_123.bin",
"format": "raw-shard",
"nbytes": 51380224,
"records": [
{
"name": "model.layers.41.mlp.gate_up_proj.q_weight",
"shape": [
28672,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 51380224,
"byteOffset": 0
}
],
"md5sum": "a5f01616e888f54345eb8ffd08308348"
},
{
"dataPath": "params_shard_124.bin",
"format": "raw-shard",
"nbytes": 25145344,
"records": [
{
"name": "model.layers.40.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.40.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.40.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.40.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.layers.41.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
},
{
"name": "model.layers.41.mlp.down_proj.q_scale",
"shape": [
3584,
112
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 802816,
"byteOffset": 22715392
},
{
"name": "model.layers.41.mlp.gate_up_proj.q_scale",
"shape": [
28672,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 23518208
},
{
"name": "model.layers.41.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25123840
},
{
"name": "model.layers.41.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25131008
},
{
"name": "model.layers.41.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 25138176
}
],
"md5sum": "e8da0215a0a2bb48ad32acd2388e7ec5"
},
{
"dataPath": "params_shard_125.bin",
"format": "raw-shard",
"nbytes": 22715392,
"records": [
{
"name": "model.layers.41.self_attn.qkv_proj.q_weight",
"shape": [
8192,
448
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 14680064,
"byteOffset": 0
},
{
"name": "model.layers.41.self_attn.qkv_proj.q_scale",
"shape": [
8192,
28
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 458752,
"byteOffset": 14680064
},
{
"name": "model.layers.41.self_attn.o_proj.q_weight",
"shape": [
3584,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15138816
},
{
"name": "model.layers.41.self_attn.o_proj.q_scale",
"shape": [
3584,
32
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 229376,
"byteOffset": 22478848
},
{
"name": "model.norm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 22708224
}
],
"md5sum": "b873fedd308e1abf48def3c541eb195e"
}
]
}