ZetAI-small / tensor-cache.json
graafhenk's picture
Qwen2.5-0.5B q0f16 — full precision, fine-tuning preserved
e0ffe35 verified
Raw History Blame Contribute Delete
69.1 kB
{
"metadata": {
"ParamSize": 170,
"ParamBytes": 988065536.0,
"BitsPerParam": 16.0
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 272269312,
"records": [
{
"name": "model.embed_tokens.weight",
"shape": [
151936,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 272269312,
"byteOffset": 0
}
],
"md5sum": "f4f80996c9cf5596e0d51753b2b1f14e"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 29826560,
"records": [
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 1792
},
{
"name": "model.layers.0.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8718080
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26150656
},
{
"name": "model.layers.0.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26152448
},
{
"name": "model.layers.0.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26154752
},
{
"name": "model.layers.0.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28219136
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29824768
}
],
"md5sum": "c3feef7f1a9c7602b22c3dd2d750d4dc"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.1.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.1.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.1.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.1.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "bf8e8cf503cd3f5ceb3f601021bd3af7"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.10.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.10.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.10.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.10.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.10.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "df9a6df0514dfd119d5e6a14c70677ea"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.11.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.11.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.11.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.11.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.11.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "b7ea89d21e6a281eada174d059714eab"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.12.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.12.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.12.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.12.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "7e6acedfb8f157ca7a51b1dbfb06476b"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.13.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.13.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.13.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.13.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "219181e47af51f7aa44693c8240a6e1f"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.14.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.14.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.14.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.14.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.14.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "bd0c428dc023e0c6b6efada206a23086"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.15.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.15.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.15.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.15.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.15.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "3ef431b7cb8161ffd6038c8e1120c31b"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.16.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.16.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.16.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.16.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.16.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "a63154660a2f35c7309221021a06f8e4"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.17.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.17.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.17.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.17.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "f62443d5fcff980bb6f55999c6abce54"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.18.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.18.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.18.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.18.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.18.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "7b475bf97df9db1da8ff9889f3c1a24f"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.19.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.19.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.19.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.19.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.19.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "d43f3e9f3c31f177eff8da9d0dadc45a"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.2.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.2.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.2.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.2.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "1eddc247ed9cbdf0cbe49ed955d40787"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.20.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.20.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.20.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.20.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.20.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "7167b7572b5c409f3daaff274a0b7027"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.21.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.21.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.21.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.21.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "fe02b8d2dbbaf1e0aead3fde15e941e6"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.22.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.22.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.22.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.22.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.22.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "f6f117053191d49eb3b157cb8e501e56"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.23.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.23.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.23.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.23.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.23.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "ef0810a7f2a303352a0536ce84664c12"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.3.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.3.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.3.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.3.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "2044ebf36286e3ccaedaf29e0c7b8691"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.4.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.4.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.4.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.4.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.4.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "658eab3c2a8b71b313e8f52b90f4f278"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.5.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.5.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.5.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.5.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "9c14fb9e4878352288cf8e7432d7d217"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.6.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.6.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.6.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.6.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "ff8621a00eae8d97d2080a859e9037cf"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.7.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.7.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.7.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.7.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.7.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "3575c0974489bcef7bcfa047f16a6bc4"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.8.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.8.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.8.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.8.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "9a1c1102a72f8a5cfb640e86c0183712"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 29824768,
"records": [
{
"name": "model.layers.9.mlp.down_proj.weight",
"shape": [
896,
4864
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8716288,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.gate_up_proj.weight",
"shape": [
9728,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 17432576,
"byteOffset": 8716288
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 26148864
},
{
"name": "model.layers.9.self_attn.c_attn.bias",
"shape": [
1152
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2304,
"byteOffset": 26150656
},
{
"name": "model.layers.9.self_attn.c_attn.weight",
"shape": [
1152,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 2064384,
"byteOffset": 26152960
},
{
"name": "model.layers.9.self_attn.o_proj.weight",
"shape": [
896,
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1605632,
"byteOffset": 28217344
},
{
"name": "model.norm.weight",
"shape": [
896
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1792,
"byteOffset": 29822976
}
],
"md5sum": "802bd128cc1eeef15d05209372b17a26"
}
]
}