julientfai's picture
Upload folder using huggingface_hub
76c5c24 verified
Raw
History Blame Contribute Delete
148 kB
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 4073857024.0,
"BitsPerParam": 3.837973340279235
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 65536000,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
32000,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 65536000,
"byteOffset": 0
}
],
"md5sum": "c0661246e6e8bb3ca9a6a481d1ed6abe"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.27.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "2d6f9b287fd5e4ff7462a7ac82b3f5d9"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.28.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "d3fa7aff50593746e494b7ce55ab5408"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "687c16a673740516a091beffe5f442a4"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 22904832,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 0
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 8192000
},
{
"name": "model.layers.27.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 8200192
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11870208
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11878400
},
{
"name": "model.layers.28.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11886592
},
{
"name": "model.layers.28.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 15556608
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22896640
}
],
"md5sum": "29ac8da54edcfdbd2d075d1c0952c087"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.29.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "df87a42e9d540874db6d87aed7e2b8be"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "8bb70a89a855ee52349064807f8de883"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.28.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.28.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.28.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.28.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.29.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "0f70622525432981ebdc3329e81a88aa"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1b370c7b2583c86c446de32605df448b"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.29.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.29.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.29.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "1cd60ba691f39204b5d5c394ae524610"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "df74bd5304476c6c4bf00ea4e7e1e8f4"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.30.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.30.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.30.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "6103abbecf6be5398216629942e68cb3"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.31.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "cc46aeb32e1a3550c81143ee4e593c94"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4f6ed1fa8ad70e8ef099ee8b8bc90ab3"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.30.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.31.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.31.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.31.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "9bb08b00c43b98aa0844cbc72d0b7ec1"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 65536000,
"records": [
{
"name": "model.embed_tokens.q_weight",
"shape": [
32000,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 65536000,
"byteOffset": 0
}
],
"md5sum": "ec49ad4f1cbf47de02608949b4e904bd"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.0.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "3a6e69f694ca0a97df4302bd99eaad76"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3a8ab853dfdd9d6922105402606f8dd8"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 30236672,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.31.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.embed_tokens.q_scale",
"shape": [
32000,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192000,
"byteOffset": 11018240
},
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 19210240
},
{
"name": "model.layers.0.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 19218432
},
{
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 22888448
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30228480
}
],
"md5sum": "a970b804a64e52161c6059d88fd41d30"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.1.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "8b5ccf9cb6fd60f39bb1ff560fe5253b"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4015901b7a3c87b6238376c31ac6526f"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.0.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.0.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.1.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "10c8e8cd595d0be3e13311bdb5829c77"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "a1255e98ac176c0035eb831661cb7054"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.1.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.1.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "3e714fc66a90b5192397dfcc1aef4911"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "634e5fb5afb49ec9ae6e632d4063c03b"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.2.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "6ae17dbe3c1471b6cc2709fbc5292128"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.3.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "609444a3f396707f3e5956d17fee09ee"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "b4d88d6e47722369eb9a32dd3efd05c8"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.3.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "f18ea12f78ab6ee5e4822d65b6129e98"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.4.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "07dce329a47064ee90ae9839c68bd813"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "26d79f632c117e31ff19ef94be01fc58"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.3.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.3.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.4.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "ab09fdb0212389048a766a9b68c88db5"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 23592960,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.4.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.4.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
}
],
"md5sum": "0a13a647409cf8f295d215c3fb50bbc2"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.10.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "5c35dd8e44d11df4af2f39ba6f23d3a7"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.11.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "a6219850aac61cfd610b478b33c635a6"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "984c3b45bfd0d5aa0b5a767b4ac93bf4"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 28868608,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 14155776
},
{
"name": "model.layers.10.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 14163968
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 17833984
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 17842176
},
{
"name": "model.layers.11.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 17850368
},
{
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 21520384
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 28860416
}
],
"md5sum": "739a19670b289474c3713c8672b39eba"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.12.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "9b1ddba4f1ad2fa18a00deb4248d2506"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "940f9c4ef28130d1de05447399c84bf5"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.11.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.11.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.12.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "7961f2c95798321d65d9f6395c3fd337"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "6c8bc9b6e1815a7873e73d224ce3b8e3"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.12.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.12.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "1736ed75494d4ae4f7ec83db0f7243be"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4a5614d6836877f8933a648bc049c23e"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.13.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "742197070f83ae7dd1582b4617101935"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.14.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "c542ae010f230b7407169e6152c78be2"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "fb813325c76716d5649cc56ca14e1b11"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.13.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.13.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.14.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "dde2dcff707cdca969dc1d09c26a944d"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.15.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "a751f9de31dced906eda2ecbb6b4d02b"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "07ed23393dc1c0ab50173effaa491f97"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.14.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.15.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "fb6ab82acc4270bee307930642f5a25f"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "d8e5119e8744a6535f6e51d00efe1603"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.15.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.15.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "3ce2ba104950fc08e9828f8b40b74ae7"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "df895d96381124d93dc43669dcbe7d65"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.16.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.16.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 23592960
}
],
"md5sum": "b0c1ed1cc1ef2268120dbe531733f5f0"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.5.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "fc69a30ef8d9b293f929f02a6887416d"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "42ab04f50b8feb9d7d00ce1ea557a6be"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.10.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.10.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.5.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "b81d36b66d56e989a73c59984375d908"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.6.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "c676b3b72f7dfcfb95d120c1208443c3"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "cbea68d553c353564b1c10b988817060"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 27811840,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.5.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 7348224
},
{
"name": "model.layers.5.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 15736832
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16785408
},
{
"name": "model.layers.6.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 16793600
},
{
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 20463616
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 27803648
}
],
"md5sum": "244a19c8a34020789d4c2e3d364009ab"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.7.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "cb55e4bb304e1cc4dab7071b9d814766"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "326d1ccaaffb9bf2ea36e31aa95eb1fd"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.6.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.6.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.7.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "0ddbd8c56770124efbe7d8473c1d9d0b"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "428186b3891824aa9c77f4e10255f1d7"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.7.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.7.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "c3ce9f8164d112663e04479521bb912a"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "ccdcc0303026df645765da6c62441448"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.8.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "c0caed58181ba345d8fa4d7380de95d1"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.9.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "c586e1257b7779ab8a5fa8b202705982"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "453dd9e3c32bbd61a3d0b995bf71ebec"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.8.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.9.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "25395a6be4e58390fe907229ea49d686"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.16.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "3cecbdf7770a1b1f58fe7794e3912fad"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.17.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "6027ad40ecda24a6f66f0399bee889c2"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "d153a44ce0243ab6335edc9feb327e65"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 25722880,
"records": [
{
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.9.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.16.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 14688256
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 14696448
},
{
"name": "model.layers.17.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 14704640
},
{
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 18374656
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 25714688
}
],
"md5sum": "dc89e792502c6e93c1a5f2e5d110084a"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.18.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "5043b45a3858073131ba058e69d9c360"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "f4b0f7db65f8758d2beaec0808ba1075"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.17.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.17.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.18.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "ebe097650fb3002f529923e328f78e99"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "8cb0594d98f517c94b406c412d9be637"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 30949376,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.18.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.18.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 30941184
}
],
"md5sum": "541940aebc7a9a45b75fb4451ebed1d4"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "2e8c3b60de85d22354d56571e4d5e3ce"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 25174016,
"records": [
{
"name": "model.layers.19.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 0
},
{
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 3670016
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 11018240
},
{
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 23601152
}
],
"md5sum": "90278266c6ea57b270c77e92984f61f2"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.20.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "d1df32ec50ffffb54a0d18b3422bace1"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "616ed8d940afa0c2283fd7459765b8d8"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.19.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.19.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.20.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "22a4a4b6ea7789dc63a845968e09f27b"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.21.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "d6ac336cba846f10c7a516b0f3b501a3"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "82bb575b702c4f0359c09fd63901b258"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.20.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.21.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "1bf4f36cc12f760fe90e47bc8e41c9c1"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 23592960,
"records": [
{
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.21.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.21.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
}
],
"md5sum": "30d8ed3b5ef57d5df21183564837c012"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.22.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "baad00ce64c6339a994d288f2f95be8b"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "29f3c825d1a00e309d45365ae184c0e4"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.22.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.22.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.22.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.22.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "c8077eacb426a8bf69464c0ce9165130"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "a338ab2c3d918d9ecf1449d6cb937648"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "80dbd08c7579c52f9f09e44a969bf0ed"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 32530432,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7348224
},
{
"name": "model.layers.23.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 7356416
},
{
"name": "model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 11026432
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18366464
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 18374656
},
{
"name": "model.layers.23.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 30957568
}
],
"md5sum": "f00f908e632985d74993dde1bb2ff604"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "ca9eb952ba672a2583171cdaa9fbe365"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "d8360a8b9a32e0564ee90606de1b2731"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 33046528,
"records": [
{
"name": "model.layers.23.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 8388608
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 9437184
},
{
"name": "model.layers.24.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 9445376
},
{
"name": "model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 13115392
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 20455424
},
{
"name": "model.layers.24.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 20463616
}
],
"md5sum": "0f0f8bb4142778c223eccce593474969"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.25.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "98604ef92a84af5b3e33f4aad042a001"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4b5dfda43daa8f123291a79517b4075d"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 22036480,
"records": [
{
"name": "model.layers.24.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 0
},
{
"name": "model.layers.24.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 1572864
},
{
"name": "model.layers.24.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 9961472
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 11010048
},
{
"name": "model.layers.25.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 11018240
},
{
"name": "model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 14688256
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22028288
}
],
"md5sum": "391782a1b183e1868e5a8c181c886db7"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.26.mlp.down_proj.q_weight",
"shape": [
4096,
1792
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "80514b87801d61da60c3746db179e4ed"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "58c97774ff66168ddfa5ce37410d3a13"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 27271168,
"records": [
{
"name": "model.layers.25.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 12582912
},
{
"name": "model.layers.25.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 14155776
},
{
"name": "model.layers.25.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 22544384
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 23592960
},
{
"name": "model.layers.26.mlp.down_proj.q_scale",
"shape": [
4096,
448
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3670016,
"byteOffset": 23601152
}
],
"md5sum": "bdad565f26c0f041a6d7adb734b0b8b7"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_weight",
"shape": [
28672,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "96bcd3c9cbd29b38363efc4879ac3d92"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 30941184,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 7340032
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7348224
},
{
"name": "model.layers.26.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19931136
},
{
"name": "model.layers.26.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21504000
},
{
"name": "model.layers.26.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29892608
}
],
"md5sum": "5f9414f8e000405842e69ef2ebe16217"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 30932992,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.q_scale",
"shape": [
28672,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7340032,
"byteOffset": 0
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_weight",
"shape": [
6144,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 12582912,
"byteOffset": 7340032
},
{
"name": "model.layers.27.self_attn.qkv_proj.q_scale",
"shape": [
6144,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1572864,
"byteOffset": 19922944
},
{
"name": "model.layers.27.self_attn.o_proj.q_weight",
"shape": [
4096,
512
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 8388608,
"byteOffset": 21495808
},
{
"name": "model.layers.27.self_attn.o_proj.q_scale",
"shape": [
4096,
128
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1048576,
"byteOffset": 29884416
}
],
"md5sum": "118bf643e6afc8c01e15dc71db4f016e"
}
]
}