|
{ |
|
"metadata": { |
|
"ParamSize": 451, |
|
"ParamBytes": 65527752704.0, |
|
"BitsPerParam": 16.0 |
|
}, |
|
"records": [ |
|
{ |
|
"dataPath": "params_shard_0.bin", |
|
"format": "raw-shard", |
|
"nbytes": 1557135360, |
|
"records": [ |
|
{ |
|
"name": "model.embed_tokens.weight", |
|
"shape": [ |
|
152064, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1557135360, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5bb8a5b3f90570fab670ef1f77ac9c3e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_1.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e6597a419099c1c43cd4be29c57d196e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_2.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "24b9b24c41981ce94a844ae7b84a4fca" |
|
}, |
|
{ |
|
"dataPath": "params_shard_3.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "66d2a6d02e0dfa37786d3f875fe2570c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_4.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "137e6e281dfbb54da20009215402e39d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_5.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "23f983a4047343827109bdfa10803d6f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_6.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8a4d6a20dcde2d5569305bd0dad74c62" |
|
}, |
|
{ |
|
"dataPath": "params_shard_7.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "77d8014389983124d15b7022d7526516" |
|
}, |
|
{ |
|
"dataPath": "params_shard_8.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.1.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9762db72d672031a8f0d4fe167340f22" |
|
}, |
|
{ |
|
"dataPath": "params_shard_9.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "910029e5425232e6cdc484e431538d29" |
|
}, |
|
{ |
|
"dataPath": "params_shard_10.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "763f5e578ec61e12d9b59054f78fa12e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_11.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fade4260f6dce70b3a91149a9ff19fe6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_12.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.2.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d9360aeef170b387fce521eeae09c8c0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_13.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9ba67a428fa8783d91f8aff30c5fa204" |
|
}, |
|
{ |
|
"dataPath": "params_shard_14.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f818e6aa2e2edc23c82bfaa9c19dc299" |
|
}, |
|
{ |
|
"dataPath": "params_shard_15.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "28612239120f6d76ecb155675c3294da" |
|
}, |
|
{ |
|
"dataPath": "params_shard_16.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.3.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2029484ef18e116825ed89fa957b84b5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_17.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9035b5634c8ff1291c4fec0fed69bb47" |
|
}, |
|
{ |
|
"dataPath": "params_shard_18.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "631e5c6439b249d078623bd6b965717c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_19.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "973ede8f5683e93977357ba065727794" |
|
}, |
|
{ |
|
"dataPath": "params_shard_20.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.4.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6ebb491df8f469da7ab4d907cbbfd8a0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_21.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f2c7323ac008313d435257021dae4e52" |
|
}, |
|
{ |
|
"dataPath": "params_shard_22.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0e668f09d3be2d97fb64f884151ff950" |
|
}, |
|
{ |
|
"dataPath": "params_shard_23.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "821d012918d5e6e079d45cd444c42917" |
|
}, |
|
{ |
|
"dataPath": "params_shard_24.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.5.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5337e0f85d730bffe3e021927573fd8e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_25.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7725d08483c8b493ea848de2f14b1ad9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_26.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5c741c4712bb1861618f202090149b62" |
|
}, |
|
{ |
|
"dataPath": "params_shard_27.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2e8241afad745644f8a2f99d0c7f9838" |
|
}, |
|
{ |
|
"dataPath": "params_shard_28.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.6.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a0b094d606bcc1ad1cd9df4b7a9ab4db" |
|
}, |
|
{ |
|
"dataPath": "params_shard_29.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "34a320d529bfd24553cc28a5e8a6c06c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_30.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5244c38090e74d4d4f5b983408dbf712" |
|
}, |
|
{ |
|
"dataPath": "params_shard_31.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c372847162cbe83824ab927c864d09ca" |
|
}, |
|
{ |
|
"dataPath": "params_shard_32.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.7.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6aa4864d6a582231ec1e151fb9e99977" |
|
}, |
|
{ |
|
"dataPath": "params_shard_33.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "af4f68273783d6352cf6eb072fb1a011" |
|
}, |
|
{ |
|
"dataPath": "params_shard_34.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d822791c6a3dff3ea9a97e331fa775ad" |
|
}, |
|
{ |
|
"dataPath": "params_shard_35.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "475fdd8e710217893a17bd2b0d9ea591" |
|
}, |
|
{ |
|
"dataPath": "params_shard_36.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.8.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e92702db75b16dc8faa6256084008e90" |
|
}, |
|
{ |
|
"dataPath": "params_shard_37.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6faaa6b61e4470c4fc7f04478198b0d2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_38.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5151e9100d868532427e91875a6bec00" |
|
}, |
|
{ |
|
"dataPath": "params_shard_39.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "76747cac27c83e2f6f5bc730e167e219" |
|
}, |
|
{ |
|
"dataPath": "params_shard_40.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.9.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "76d5ca076c87c580ac3b3dab806a9b0e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_41.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e2cd5b97c22a45620532f16c7462c69b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_42.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "22ae0c02dd8d5e5aa643a7a9440f4368" |
|
}, |
|
{ |
|
"dataPath": "params_shard_43.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4aecf6430e5c2620a22acf8e1a2b6e73" |
|
}, |
|
{ |
|
"dataPath": "params_shard_44.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.10.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b17a9ebc98f808a9025f19b1ed6a17db" |
|
}, |
|
{ |
|
"dataPath": "params_shard_45.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3ed98425823cef619474d4d39a670157" |
|
}, |
|
{ |
|
"dataPath": "params_shard_46.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1064b066ecbfe7ee2bd951d9f4750ebb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_47.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8866e24e57b9a5f5c78e365aff76db0e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_48.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.11.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f0ac27a56537e4246aabd88563a9f24a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_49.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5b4d6ca1eee3ed5c6e58f7626f08a3fb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_50.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "11224a0cf6a0cd951fdb9b851e61463c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_51.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "43e824cc215726669e431084226e616d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_52.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.12.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "34ad009c6731873d812aa2d9d4295a15" |
|
}, |
|
{ |
|
"dataPath": "params_shard_53.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c3fb9a5d64e782a92dcb9d1e63149905" |
|
}, |
|
{ |
|
"dataPath": "params_shard_54.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7207e14b18ee95cf7e6de2b5362e5894" |
|
}, |
|
{ |
|
"dataPath": "params_shard_55.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4997550468591f2266d7a264e2ef6cf3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_56.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.13.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3e9b72fb556280e9d3f63220b431ecc8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_57.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "38d0d2bcde8ba72881a846fa6b211c51" |
|
}, |
|
{ |
|
"dataPath": "params_shard_58.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "41823cfc9490cbffea61c80e27c4e2de" |
|
}, |
|
{ |
|
"dataPath": "params_shard_59.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "614665d4f6f73f8808dfa56b874831c3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_60.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.14.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b04bbca8f2b24ffd161c96cd1c80bed3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_61.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "da0a1979c9e5f83486bb1906c66c5321" |
|
}, |
|
{ |
|
"dataPath": "params_shard_62.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5b990ddfa3efdc6477c867a9dabb99ea" |
|
}, |
|
{ |
|
"dataPath": "params_shard_63.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "41700d40396b9ee86300e78ab60e382f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_64.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.15.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "582555dcb8d4934ae8bfe207ef4d7c70" |
|
}, |
|
{ |
|
"dataPath": "params_shard_65.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9f338f584c2e0d6e4e4cce95d7c16139" |
|
}, |
|
{ |
|
"dataPath": "params_shard_66.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c5651e6aa4d573eeed1cdec6cfc24d3b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_67.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "88e8931c30c1ab4946e247b5a8ec1388" |
|
}, |
|
{ |
|
"dataPath": "params_shard_68.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.16.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4116f1d99431d05db725e55cfea6ed87" |
|
}, |
|
{ |
|
"dataPath": "params_shard_69.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "61e768c4137c4d0aa8262b79b33d4cb6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_70.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "40b742c1586462539b2b80218ccd024a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_71.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "33730e7eb6619743821b97022b574012" |
|
}, |
|
{ |
|
"dataPath": "params_shard_72.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.17.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "53026d1b33f654bdd0090b39ab4e2c59" |
|
}, |
|
{ |
|
"dataPath": "params_shard_73.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "27dc5a70ed9a2a995fe175e0286d6af9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_74.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "840eb844b8ca3ada553ac02d41938df0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_75.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cfbf879fe49d3f372aca71b62f954158" |
|
}, |
|
{ |
|
"dataPath": "params_shard_76.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.18.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "34f70fefefb09109642b3ef2a9cdbb41" |
|
}, |
|
{ |
|
"dataPath": "params_shard_77.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0080130c55c3ed246a4853eb0aaba83c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_78.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cae00c5cc3484e8983bc697b7eccc96f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_79.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e447056cdff3c65578ae4fcc5e4c8461" |
|
}, |
|
{ |
|
"dataPath": "params_shard_80.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.19.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "80f9dc335c2e7ed0cc642c576641cb67" |
|
}, |
|
{ |
|
"dataPath": "params_shard_81.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f04793095f233c2b1202a105d4f47f03" |
|
}, |
|
{ |
|
"dataPath": "params_shard_82.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3310290e093e5d94994c997d9ce3ed2f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_83.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bfc65d8fd073d15fc92b515dd6b05730" |
|
}, |
|
{ |
|
"dataPath": "params_shard_84.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.20.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "58191c656d371b9ab0f8091ef0f28fbb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_85.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f902b44d442a2ff31b9a9ff6328a3af6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_86.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "48c952dbac55ce490db29e17c3375fa6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_87.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "705af3839ae8608b5598aab5a496a994" |
|
}, |
|
{ |
|
"dataPath": "params_shard_88.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.21.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4fcc7d40ee8f8e949969adc7a898fd5d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_89.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "db996b7293ff02ec684eb5c39f5ff6e7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_90.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "00562b416b83e897ee970faf464230c7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_91.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e7d3987e7131fbc2dd6380a5f52a97bb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_92.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.22.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "47cb7058f5e65f7c420956f93d060aba" |
|
}, |
|
{ |
|
"dataPath": "params_shard_93.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9be8911f568964b9cc32a573e2dd216f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_94.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5bda4c61695c5be0e2a621dcdae1ba16" |
|
}, |
|
{ |
|
"dataPath": "params_shard_95.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "133d055cd9417e7e9de1c5a307cfc649" |
|
}, |
|
{ |
|
"dataPath": "params_shard_96.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.23.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6fb3e57707f301c52913e683a06589e4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_97.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a13369d32c39f4d6b10e5967c1b22e51" |
|
}, |
|
{ |
|
"dataPath": "params_shard_98.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "327caba6641586d6cb9c2df2e29f9090" |
|
}, |
|
{ |
|
"dataPath": "params_shard_99.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d0c21163257ea02bb6bc2895f955b61e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_100.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.24.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ff3747e41a35848722f9bd5a197485f9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_101.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4dc76defba3461d5fb480d2b740709d0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_102.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "558719ca91923f95400f1a3c072e9710" |
|
}, |
|
{ |
|
"dataPath": "params_shard_103.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "631aca388dedc71ea348edc0cebe2893" |
|
}, |
|
{ |
|
"dataPath": "params_shard_104.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.25.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d1251b8754079e13bcaa3c51596d8049" |
|
}, |
|
{ |
|
"dataPath": "params_shard_105.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2215f94fcc3ce367a44ac620f3b5e642" |
|
}, |
|
{ |
|
"dataPath": "params_shard_106.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "85dfa43c7b957a51920e8a4c2de2e784" |
|
}, |
|
{ |
|
"dataPath": "params_shard_107.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8b2e517104941f58625337afaa3eae8f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_108.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.26.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "29714eb5d7311c54209d7d61dadf1166" |
|
}, |
|
{ |
|
"dataPath": "params_shard_109.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "56fb1365ea37063c1e55c04bc55502d2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_110.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1e2de2b002b8dc32c6561f8ddc4bc719" |
|
}, |
|
{ |
|
"dataPath": "params_shard_111.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3b30848d42b6adccf53b4209294250d3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_112.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.27.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0c4f9cf81a7dc66935ce08eed8394ec5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_113.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3c2d08ce8a85857329205b31e56815d9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_114.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c3aa209370ac55d4b9259243a22a508a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_115.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "dcb5bfbfef3ac69b5e42299d61170a1c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_116.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.28.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ce3732421604dc99ec48e6584d9350d8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_117.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a5a2b8cd5b45a1704365d3bdc5f145f3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_118.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "28bc61914b94debc2cc8fd7b18ae8690" |
|
}, |
|
{ |
|
"dataPath": "params_shard_119.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d082f7e7c84ebdb0eec10dee4acfb398" |
|
}, |
|
{ |
|
"dataPath": "params_shard_120.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.29.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "299ccc409de9e95db3ad8d6475e1cab1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_121.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9bf54df154325867a3bb8d91dbf6a168" |
|
}, |
|
{ |
|
"dataPath": "params_shard_122.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "02f634ee62f28d6e752283d96525f40f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_123.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "582341a0cc3d5cebd47b8aa07910c056" |
|
}, |
|
{ |
|
"dataPath": "params_shard_124.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.30.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7e2fcaa76a2f5350d1ac64e4c9815848" |
|
}, |
|
{ |
|
"dataPath": "params_shard_125.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "eaab4b81d2e263a778fb4a7481436ce0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_126.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ecfb57595c11a9596a98f023ef358595" |
|
}, |
|
{ |
|
"dataPath": "params_shard_127.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3cfaadb61d0f7d324774f199ff4e52b4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_128.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.31.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7bae7c0d12f50f9354cb8b4baeb18b14" |
|
}, |
|
{ |
|
"dataPath": "params_shard_129.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.32.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ef27014d8281d2c8c84004aeaaa49fda" |
|
}, |
|
{ |
|
"dataPath": "params_shard_130.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.32.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "60400f5f6827713e11e208d98fd8e15f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_131.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.32.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5026c050be4c53f6bb6bfa47486b54f6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_132.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.32.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "142830fbd23e8ff6b53ceab61ebf1979" |
|
}, |
|
{ |
|
"dataPath": "params_shard_133.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.33.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c6da48447f09539c812edbf2fced51cb" |
|
}, |
|
{ |
|
"dataPath": "params_shard_134.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.33.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c6272eceeb1035896e3c4e837acfcfb5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_135.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.33.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7dc926e16acf28fc526cf7dc1e71b54d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_136.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.33.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "17b343671d2bb6844df42549f24d5834" |
|
}, |
|
{ |
|
"dataPath": "params_shard_137.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.34.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3f26ac8c0935ad3c6ff79164ab511c88" |
|
}, |
|
{ |
|
"dataPath": "params_shard_138.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.34.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a27c32ec00e8a486aded43840dba88ec" |
|
}, |
|
{ |
|
"dataPath": "params_shard_139.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.34.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0fef21c50581598396fe76724d5adad8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_140.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.34.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e1f743d39b5022ee5b6cb9f0c5f26341" |
|
}, |
|
{ |
|
"dataPath": "params_shard_141.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.35.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9a9b8f2c99f0877bd4d7650aa0dc7b3f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_142.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.35.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "45a681debc84cf58f820652a1d1c25e8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_143.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.35.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "97ecc35cb712baadb339e33ac16bba45" |
|
}, |
|
{ |
|
"dataPath": "params_shard_144.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.35.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "dd4766fd94459eabb48ab284586a8b5a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_145.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.36.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4141e6e9be73c1479c40d15b04153b16" |
|
}, |
|
{ |
|
"dataPath": "params_shard_146.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.36.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "71f9cba9f090b4a1076f58da247ea4e9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_147.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.36.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "311ff3bf3d7f70d44b091c8f62a40c99" |
|
}, |
|
{ |
|
"dataPath": "params_shard_148.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.36.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "79a9ca8b876de58bdceeb383df00e8be" |
|
}, |
|
{ |
|
"dataPath": "params_shard_149.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.37.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2606bf667931713e0bb41b2d7c6984b4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_150.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.37.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "698cb3cc6a99812498e81eb49a85208f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_151.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.37.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ae075f5be1c8e962579372377dec30ed" |
|
}, |
|
{ |
|
"dataPath": "params_shard_152.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.37.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9a3af1f47423b6a513eb7c4e716903fc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_153.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.38.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d6d1d6ac23608d9b96f64df1f85708b9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_154.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.38.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ac39a404e1a372c22f08759e1f504943" |
|
}, |
|
{ |
|
"dataPath": "params_shard_155.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.38.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b0be55f53a230dc807f5798eabeee63d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_156.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.38.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "00650dc91f8311553efc2c36ddd73238" |
|
}, |
|
{ |
|
"dataPath": "params_shard_157.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.39.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f844a7d141d2d62065008b768d073852" |
|
}, |
|
{ |
|
"dataPath": "params_shard_158.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.39.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "901827c01833a3a7f8a60320c11de6db" |
|
}, |
|
{ |
|
"dataPath": "params_shard_159.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.39.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "98cdd2d4df2f4cdff295514ec36e1642" |
|
}, |
|
{ |
|
"dataPath": "params_shard_160.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.39.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "91d3f9a6cd1ee9801ef26833ba7d25af" |
|
}, |
|
{ |
|
"dataPath": "params_shard_161.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.40.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "83271587ca913823982f17a4ac102283" |
|
}, |
|
{ |
|
"dataPath": "params_shard_162.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.40.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8eb24239b724d0278ce28e0343df6c5d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_163.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.40.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8a9b5471ee4c0691b735ec964825f112" |
|
}, |
|
{ |
|
"dataPath": "params_shard_164.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.40.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4272e0764717ab4d8228f61f59df5637" |
|
}, |
|
{ |
|
"dataPath": "params_shard_165.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.41.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8f1e0035f7128b1a23db1712e97629b6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_166.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.41.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c4439ad3e1399dcf3ee9b5342841d551" |
|
}, |
|
{ |
|
"dataPath": "params_shard_167.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.41.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "fad38fd7ef77b7e77e7e24508f393159" |
|
}, |
|
{ |
|
"dataPath": "params_shard_168.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.41.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0f39f57b65abe17d7fc0632ba586e966" |
|
}, |
|
{ |
|
"dataPath": "params_shard_169.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.42.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0b7601915f5afc9f7e1e0b1501b60a7a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_170.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.42.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "25ec1b43287ba1eb056ffb2f9cb4c834" |
|
}, |
|
{ |
|
"dataPath": "params_shard_171.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.42.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "12ef863498b9c2bbfecea688fdafc9d6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_172.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.42.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "64c1c629f3887b91969f37b39d72ae68" |
|
}, |
|
{ |
|
"dataPath": "params_shard_173.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.43.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e529d9569cc6c8fc537e854008557ac8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_174.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.43.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5bfde37ddb51dfeab5a711738d526ee9" |
|
}, |
|
{ |
|
"dataPath": "params_shard_175.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.43.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7907afb587cc6528ef5e4d953a854df0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_176.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.43.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bbd6ecc47cb136ba32741f93754b0dd2" |
|
}, |
|
{ |
|
"dataPath": "params_shard_177.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.44.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ff49168b89309fe16e92b66206e05d96" |
|
}, |
|
{ |
|
"dataPath": "params_shard_178.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.44.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "26a702696cb3f3f484a8db6110bca751" |
|
}, |
|
{ |
|
"dataPath": "params_shard_179.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.44.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "198ea2e28f6e201a61cdd30c75dcb8e7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_180.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.44.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bec3f8b937f11cf3d664b409f5ea6057" |
|
}, |
|
{ |
|
"dataPath": "params_shard_181.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.45.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6fdaeaa33d4b81f715f361b6afe459e7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_182.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.45.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e43428db02e9286bba46cabd4c463b3c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_183.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.45.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1f0d428e75cd3fb548672181d0eb781d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_184.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.45.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "530769245540547940930efe1146fe80" |
|
}, |
|
{ |
|
"dataPath": "params_shard_185.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.46.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e3e814f34cd14d07db4f6a572d55c9e1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_186.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.46.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f5f38b93cd367de9077c8522d3e89ec8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_187.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.46.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e5515400ef6fa93ad9648a71b147c462" |
|
}, |
|
{ |
|
"dataPath": "params_shard_188.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.46.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d720702a929d7c82a2646e47650659b3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_189.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.47.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7040da6c4f8c0b1fcb4698e5e37b9cf6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_190.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.47.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "704dc3c67edcb5519afd8c374f9ba11b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_191.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.47.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9a53a4d4f08d965ae9d1099618b0ccbd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_192.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.47.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "bee6c9d6e21fc88b1baee8985c74f922" |
|
}, |
|
{ |
|
"dataPath": "params_shard_193.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.48.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d9bd87b3cb6496b12fb0d7cd7e450936" |
|
}, |
|
{ |
|
"dataPath": "params_shard_194.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.48.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "39d72169d267ab949d8de70fe3aabd4a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_195.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.48.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "18dcb3f4919decf0f5f449cc1733d5d4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_196.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.48.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "0be019a0f15bc769d793c95661a5dcc7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_197.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.49.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b887737aa636be3b55dace81970e75a8" |
|
}, |
|
{ |
|
"dataPath": "params_shard_198.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.49.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "001453fc2c9c048686d4aac00c5aa6be" |
|
}, |
|
{ |
|
"dataPath": "params_shard_199.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.49.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b1a0dafb138d633f8f48a490f6cb081e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_200.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.49.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1c4a8a27e54976fa34a4e792a2ffbf69" |
|
}, |
|
{ |
|
"dataPath": "params_shard_201.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.50.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "40e5824b7840372866c1f1a77a5dcb57" |
|
}, |
|
{ |
|
"dataPath": "params_shard_202.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.50.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "156056edf699aae9119d6d24dd486814" |
|
}, |
|
{ |
|
"dataPath": "params_shard_203.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.50.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "e0b77aa1a744122a50347933aa9ff8b0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_204.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.50.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3879245b6ab386bb79efed4149c8f0ec" |
|
}, |
|
{ |
|
"dataPath": "params_shard_205.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.51.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1ff4d05b384325507eff9a48f25a6528" |
|
}, |
|
{ |
|
"dataPath": "params_shard_206.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.51.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "a319036fd908ecd26e5b7be2d3ac99c0" |
|
}, |
|
{ |
|
"dataPath": "params_shard_207.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.51.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4e86c388bdb016245306e5de97ece315" |
|
}, |
|
{ |
|
"dataPath": "params_shard_208.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.51.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ad862495e7b6b15e765950047841ca92" |
|
}, |
|
{ |
|
"dataPath": "params_shard_209.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.52.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "54ddd0cfa009c8521f8f19bce2a1bae6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_210.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.52.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d396daa1c725f866c6e245bd41e9c13c" |
|
}, |
|
{ |
|
"dataPath": "params_shard_211.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.52.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1bd8faa3795441a9fd43fe49ac267625" |
|
}, |
|
{ |
|
"dataPath": "params_shard_212.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.52.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "05bf0310a7ede7f8f89938bbd882f69e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_213.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.53.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "07864b3e538c544a2bc0b4d5f95bfd42" |
|
}, |
|
{ |
|
"dataPath": "params_shard_214.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.53.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9dc0d01c408bbc93852be82d8874c3f4" |
|
}, |
|
{ |
|
"dataPath": "params_shard_215.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.53.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cb9aedf51a3787dc3de0e8c0942dd576" |
|
}, |
|
{ |
|
"dataPath": "params_shard_216.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.53.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "770c7ff748a6ec580244b77d624291e6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_217.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.54.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d6097dc03c1afcc4e835cc049cd8e476" |
|
}, |
|
{ |
|
"dataPath": "params_shard_218.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.54.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d16dd0c01816ef77a7dc6a42a8d7274a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_219.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.54.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "2855a99f3f66a268d2a552b25c368362" |
|
}, |
|
{ |
|
"dataPath": "params_shard_220.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.54.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "90b19b11cc36736d62f0ec62031ed932" |
|
}, |
|
{ |
|
"dataPath": "params_shard_221.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.55.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "942bb5033d93fd5d0b9c7442b130cd3e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_222.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.55.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ef1211d6f8c0f9aa26904b5ba944ca9e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_223.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.55.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "783775ab1f7e66d1ec63083117406e3a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_224.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.55.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "9db67b492edf4a42f11963b64606bf1e" |
|
}, |
|
{ |
|
"dataPath": "params_shard_225.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.56.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8e09250600b094fc423a4a477072b4b5" |
|
}, |
|
{ |
|
"dataPath": "params_shard_226.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.56.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "693cde303f1568b135c6239d5b3a6c09" |
|
}, |
|
{ |
|
"dataPath": "params_shard_227.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.56.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c3991c32e3c7bdd85c638d15ecc4cfdd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_228.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.56.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1be4d9c086729e2ba158676eff58cb2d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_229.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.57.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6ecd08921ccd3a6ae4aa74fa54e80568" |
|
}, |
|
{ |
|
"dataPath": "params_shard_230.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.57.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "b3b30d99acb175f55ea71647a359d65f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_231.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.57.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7fda90bdfce6c66cd1a43991fd65b228" |
|
}, |
|
{ |
|
"dataPath": "params_shard_232.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.57.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "f6748133b33d9f225f6695f6ec90e69b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_233.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.58.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "591b4b01d65d9dd75cef67d44f3cf108" |
|
}, |
|
{ |
|
"dataPath": "params_shard_234.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.58.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ba2c28ef58f96b14cc0d62f00d3cf822" |
|
}, |
|
{ |
|
"dataPath": "params_shard_235.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.58.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "265b37be417087570718f4c5aeaf1aaf" |
|
}, |
|
{ |
|
"dataPath": "params_shard_236.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.58.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "215e06ba9a43e580daaa27b9be7c4566" |
|
}, |
|
{ |
|
"dataPath": "params_shard_237.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.59.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "7d932e08eef1f7fe2e33f989dc7b31fe" |
|
}, |
|
{ |
|
"dataPath": "params_shard_238.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.59.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "18014a0f00bc42b559fe959b3317a5cc" |
|
}, |
|
{ |
|
"dataPath": "params_shard_239.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.59.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "87fe39f5d118ad57d1620a9ca382e484" |
|
}, |
|
{ |
|
"dataPath": "params_shard_240.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.59.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "3401a526e41305b5a01e50b22d6cbbf7" |
|
}, |
|
{ |
|
"dataPath": "params_shard_241.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.60.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "16715deee54206a1dd1cc36d475889d1" |
|
}, |
|
{ |
|
"dataPath": "params_shard_242.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.60.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cd283d94a653c17841bb0b5e968cb85b" |
|
}, |
|
{ |
|
"dataPath": "params_shard_243.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.60.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6059533c022293d3644a9fef658d869d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_244.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.60.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "cdf26331534e5f7dec47a3cffcc4eb9a" |
|
}, |
|
{ |
|
"dataPath": "params_shard_245.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.61.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "1fb8245ffc024f4be7f01f9a71191e87" |
|
}, |
|
{ |
|
"dataPath": "params_shard_246.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.61.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "ef30f7179eda98b1fbc1a1c6210223db" |
|
}, |
|
{ |
|
"dataPath": "params_shard_247.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.61.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "83bb5fa0c08a971724114a3c29c1ca22" |
|
}, |
|
{ |
|
"dataPath": "params_shard_248.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.61.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "c6d9ce99af9895b2fd3fddd3bab8826f" |
|
}, |
|
{ |
|
"dataPath": "params_shard_249.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.62.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "398bb01614c1e696e914c733040601be" |
|
}, |
|
{ |
|
"dataPath": "params_shard_250.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.62.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "00ff229b5cbc95cbfa645a3ecfefe0d3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_251.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.62.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "5a6e855369f745008643878409e71ea3" |
|
}, |
|
{ |
|
"dataPath": "params_shard_252.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.62.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "6a86f5facc7b817968d67cd5bf9dda98" |
|
}, |
|
{ |
|
"dataPath": "params_shard_253.bin", |
|
"format": "raw-shard", |
|
"nbytes": 73400320, |
|
"records": [ |
|
{ |
|
"name": "model.layers.63.self_attn.c_attn.weight", |
|
"shape": [ |
|
7168, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 73400320, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "d4e8d7bb35448a8b31f244c1243911a6" |
|
}, |
|
{ |
|
"dataPath": "params_shard_254.bin", |
|
"format": "raw-shard", |
|
"nbytes": 52428800, |
|
"records": [ |
|
{ |
|
"name": "model.layers.63.self_attn.o_proj.weight", |
|
"shape": [ |
|
5120, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 52428800, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "07c1f2352cb9a36fd8b82c1ef6b5ce1d" |
|
}, |
|
{ |
|
"dataPath": "params_shard_255.bin", |
|
"format": "raw-shard", |
|
"nbytes": 566231040, |
|
"records": [ |
|
{ |
|
"name": "model.layers.63.mlp.gate_up_proj.weight", |
|
"shape": [ |
|
55296, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 566231040, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "86f9a1a6306e0328a4ffb3a8df04fcbd" |
|
}, |
|
{ |
|
"dataPath": "params_shard_256.bin", |
|
"format": "raw-shard", |
|
"nbytes": 283115520, |
|
"records": [ |
|
{ |
|
"name": "model.layers.63.mlp.down_proj.weight", |
|
"shape": [ |
|
5120, |
|
27648 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 283115520, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "8bcfa1c7505bae13d354d3048e808dad" |
|
}, |
|
{ |
|
"dataPath": "params_shard_257.bin", |
|
"format": "raw-shard", |
|
"nbytes": 1557135360, |
|
"records": [ |
|
{ |
|
"name": "lm_head.weight", |
|
"shape": [ |
|
152064, |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 1557135360, |
|
"byteOffset": 0 |
|
} |
|
], |
|
"md5sum": "4be679607519c7d97cc3fffcbb26d953" |
|
}, |
|
{ |
|
"dataPath": "params_shard_258.bin", |
|
"format": "raw-shard", |
|
"nbytes": 2238464, |
|
"records": [ |
|
{ |
|
"name": "model.layers.0.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 0 |
|
}, |
|
{ |
|
"name": "model.layers.0.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 14336 |
|
}, |
|
{ |
|
"name": "model.layers.0.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 24576 |
|
}, |
|
{ |
|
"name": "model.layers.1.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 34816 |
|
}, |
|
{ |
|
"name": "model.layers.1.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 49152 |
|
}, |
|
{ |
|
"name": "model.layers.1.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 59392 |
|
}, |
|
{ |
|
"name": "model.layers.2.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 69632 |
|
}, |
|
{ |
|
"name": "model.layers.2.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 83968 |
|
}, |
|
{ |
|
"name": "model.layers.2.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 94208 |
|
}, |
|
{ |
|
"name": "model.layers.3.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 104448 |
|
}, |
|
{ |
|
"name": "model.layers.3.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 118784 |
|
}, |
|
{ |
|
"name": "model.layers.3.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 129024 |
|
}, |
|
{ |
|
"name": "model.layers.4.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 139264 |
|
}, |
|
{ |
|
"name": "model.layers.4.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 153600 |
|
}, |
|
{ |
|
"name": "model.layers.4.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 163840 |
|
}, |
|
{ |
|
"name": "model.layers.5.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 174080 |
|
}, |
|
{ |
|
"name": "model.layers.5.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 188416 |
|
}, |
|
{ |
|
"name": "model.layers.5.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 198656 |
|
}, |
|
{ |
|
"name": "model.layers.6.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 208896 |
|
}, |
|
{ |
|
"name": "model.layers.6.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 223232 |
|
}, |
|
{ |
|
"name": "model.layers.6.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 233472 |
|
}, |
|
{ |
|
"name": "model.layers.7.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 243712 |
|
}, |
|
{ |
|
"name": "model.layers.7.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 258048 |
|
}, |
|
{ |
|
"name": "model.layers.7.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 268288 |
|
}, |
|
{ |
|
"name": "model.layers.8.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 278528 |
|
}, |
|
{ |
|
"name": "model.layers.8.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 292864 |
|
}, |
|
{ |
|
"name": "model.layers.8.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 303104 |
|
}, |
|
{ |
|
"name": "model.layers.9.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 313344 |
|
}, |
|
{ |
|
"name": "model.layers.9.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 327680 |
|
}, |
|
{ |
|
"name": "model.layers.9.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 337920 |
|
}, |
|
{ |
|
"name": "model.layers.10.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 348160 |
|
}, |
|
{ |
|
"name": "model.layers.10.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 362496 |
|
}, |
|
{ |
|
"name": "model.layers.10.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 372736 |
|
}, |
|
{ |
|
"name": "model.layers.11.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 382976 |
|
}, |
|
{ |
|
"name": "model.layers.11.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 397312 |
|
}, |
|
{ |
|
"name": "model.layers.11.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 407552 |
|
}, |
|
{ |
|
"name": "model.layers.12.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 417792 |
|
}, |
|
{ |
|
"name": "model.layers.12.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 432128 |
|
}, |
|
{ |
|
"name": "model.layers.12.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 442368 |
|
}, |
|
{ |
|
"name": "model.layers.13.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 452608 |
|
}, |
|
{ |
|
"name": "model.layers.13.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 466944 |
|
}, |
|
{ |
|
"name": "model.layers.13.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 477184 |
|
}, |
|
{ |
|
"name": "model.layers.14.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 487424 |
|
}, |
|
{ |
|
"name": "model.layers.14.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 501760 |
|
}, |
|
{ |
|
"name": "model.layers.14.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 512000 |
|
}, |
|
{ |
|
"name": "model.layers.15.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 522240 |
|
}, |
|
{ |
|
"name": "model.layers.15.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 536576 |
|
}, |
|
{ |
|
"name": "model.layers.15.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 546816 |
|
}, |
|
{ |
|
"name": "model.layers.16.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 557056 |
|
}, |
|
{ |
|
"name": "model.layers.16.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 571392 |
|
}, |
|
{ |
|
"name": "model.layers.16.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 581632 |
|
}, |
|
{ |
|
"name": "model.layers.17.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 591872 |
|
}, |
|
{ |
|
"name": "model.layers.17.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 606208 |
|
}, |
|
{ |
|
"name": "model.layers.17.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 616448 |
|
}, |
|
{ |
|
"name": "model.layers.18.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 626688 |
|
}, |
|
{ |
|
"name": "model.layers.18.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 641024 |
|
}, |
|
{ |
|
"name": "model.layers.18.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 651264 |
|
}, |
|
{ |
|
"name": "model.layers.19.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 661504 |
|
}, |
|
{ |
|
"name": "model.layers.19.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 675840 |
|
}, |
|
{ |
|
"name": "model.layers.19.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 686080 |
|
}, |
|
{ |
|
"name": "model.layers.20.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 696320 |
|
}, |
|
{ |
|
"name": "model.layers.20.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 710656 |
|
}, |
|
{ |
|
"name": "model.layers.20.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 720896 |
|
}, |
|
{ |
|
"name": "model.layers.21.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 731136 |
|
}, |
|
{ |
|
"name": "model.layers.21.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 745472 |
|
}, |
|
{ |
|
"name": "model.layers.21.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 755712 |
|
}, |
|
{ |
|
"name": "model.layers.22.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 765952 |
|
}, |
|
{ |
|
"name": "model.layers.22.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 780288 |
|
}, |
|
{ |
|
"name": "model.layers.22.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 790528 |
|
}, |
|
{ |
|
"name": "model.layers.23.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 800768 |
|
}, |
|
{ |
|
"name": "model.layers.23.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 815104 |
|
}, |
|
{ |
|
"name": "model.layers.23.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 825344 |
|
}, |
|
{ |
|
"name": "model.layers.24.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 835584 |
|
}, |
|
{ |
|
"name": "model.layers.24.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 849920 |
|
}, |
|
{ |
|
"name": "model.layers.24.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 860160 |
|
}, |
|
{ |
|
"name": "model.layers.25.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 870400 |
|
}, |
|
{ |
|
"name": "model.layers.25.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 884736 |
|
}, |
|
{ |
|
"name": "model.layers.25.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 894976 |
|
}, |
|
{ |
|
"name": "model.layers.26.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 905216 |
|
}, |
|
{ |
|
"name": "model.layers.26.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 919552 |
|
}, |
|
{ |
|
"name": "model.layers.26.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 929792 |
|
}, |
|
{ |
|
"name": "model.layers.27.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 940032 |
|
}, |
|
{ |
|
"name": "model.layers.27.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 954368 |
|
}, |
|
{ |
|
"name": "model.layers.27.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 964608 |
|
}, |
|
{ |
|
"name": "model.layers.28.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 974848 |
|
}, |
|
{ |
|
"name": "model.layers.28.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 989184 |
|
}, |
|
{ |
|
"name": "model.layers.28.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 999424 |
|
}, |
|
{ |
|
"name": "model.layers.29.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1009664 |
|
}, |
|
{ |
|
"name": "model.layers.29.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1024000 |
|
}, |
|
{ |
|
"name": "model.layers.29.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1034240 |
|
}, |
|
{ |
|
"name": "model.layers.30.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1044480 |
|
}, |
|
{ |
|
"name": "model.layers.30.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1058816 |
|
}, |
|
{ |
|
"name": "model.layers.30.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1069056 |
|
}, |
|
{ |
|
"name": "model.layers.31.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1079296 |
|
}, |
|
{ |
|
"name": "model.layers.31.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1093632 |
|
}, |
|
{ |
|
"name": "model.layers.31.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1103872 |
|
}, |
|
{ |
|
"name": "model.layers.32.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1114112 |
|
}, |
|
{ |
|
"name": "model.layers.32.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1128448 |
|
}, |
|
{ |
|
"name": "model.layers.32.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1138688 |
|
}, |
|
{ |
|
"name": "model.layers.33.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1148928 |
|
}, |
|
{ |
|
"name": "model.layers.33.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1163264 |
|
}, |
|
{ |
|
"name": "model.layers.33.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1173504 |
|
}, |
|
{ |
|
"name": "model.layers.34.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1183744 |
|
}, |
|
{ |
|
"name": "model.layers.34.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1198080 |
|
}, |
|
{ |
|
"name": "model.layers.34.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1208320 |
|
}, |
|
{ |
|
"name": "model.layers.35.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1218560 |
|
}, |
|
{ |
|
"name": "model.layers.35.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1232896 |
|
}, |
|
{ |
|
"name": "model.layers.35.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1243136 |
|
}, |
|
{ |
|
"name": "model.layers.36.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1253376 |
|
}, |
|
{ |
|
"name": "model.layers.36.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1267712 |
|
}, |
|
{ |
|
"name": "model.layers.36.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1277952 |
|
}, |
|
{ |
|
"name": "model.layers.37.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1288192 |
|
}, |
|
{ |
|
"name": "model.layers.37.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1302528 |
|
}, |
|
{ |
|
"name": "model.layers.37.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1312768 |
|
}, |
|
{ |
|
"name": "model.layers.38.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1323008 |
|
}, |
|
{ |
|
"name": "model.layers.38.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1337344 |
|
}, |
|
{ |
|
"name": "model.layers.38.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1347584 |
|
}, |
|
{ |
|
"name": "model.layers.39.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1357824 |
|
}, |
|
{ |
|
"name": "model.layers.39.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1372160 |
|
}, |
|
{ |
|
"name": "model.layers.39.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1382400 |
|
}, |
|
{ |
|
"name": "model.layers.40.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1392640 |
|
}, |
|
{ |
|
"name": "model.layers.40.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1406976 |
|
}, |
|
{ |
|
"name": "model.layers.40.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1417216 |
|
}, |
|
{ |
|
"name": "model.layers.41.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1427456 |
|
}, |
|
{ |
|
"name": "model.layers.41.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1441792 |
|
}, |
|
{ |
|
"name": "model.layers.41.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1452032 |
|
}, |
|
{ |
|
"name": "model.layers.42.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1462272 |
|
}, |
|
{ |
|
"name": "model.layers.42.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1476608 |
|
}, |
|
{ |
|
"name": "model.layers.42.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1486848 |
|
}, |
|
{ |
|
"name": "model.layers.43.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1497088 |
|
}, |
|
{ |
|
"name": "model.layers.43.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1511424 |
|
}, |
|
{ |
|
"name": "model.layers.43.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1521664 |
|
}, |
|
{ |
|
"name": "model.layers.44.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1531904 |
|
}, |
|
{ |
|
"name": "model.layers.44.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1546240 |
|
}, |
|
{ |
|
"name": "model.layers.44.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1556480 |
|
}, |
|
{ |
|
"name": "model.layers.45.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1566720 |
|
}, |
|
{ |
|
"name": "model.layers.45.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1581056 |
|
}, |
|
{ |
|
"name": "model.layers.45.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1591296 |
|
}, |
|
{ |
|
"name": "model.layers.46.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1601536 |
|
}, |
|
{ |
|
"name": "model.layers.46.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1615872 |
|
}, |
|
{ |
|
"name": "model.layers.46.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1626112 |
|
}, |
|
{ |
|
"name": "model.layers.47.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1636352 |
|
}, |
|
{ |
|
"name": "model.layers.47.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1650688 |
|
}, |
|
{ |
|
"name": "model.layers.47.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1660928 |
|
}, |
|
{ |
|
"name": "model.layers.48.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1671168 |
|
}, |
|
{ |
|
"name": "model.layers.48.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1685504 |
|
}, |
|
{ |
|
"name": "model.layers.48.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1695744 |
|
}, |
|
{ |
|
"name": "model.layers.49.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1705984 |
|
}, |
|
{ |
|
"name": "model.layers.49.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1720320 |
|
}, |
|
{ |
|
"name": "model.layers.49.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1730560 |
|
}, |
|
{ |
|
"name": "model.layers.50.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1740800 |
|
}, |
|
{ |
|
"name": "model.layers.50.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1755136 |
|
}, |
|
{ |
|
"name": "model.layers.50.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1765376 |
|
}, |
|
{ |
|
"name": "model.layers.51.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1775616 |
|
}, |
|
{ |
|
"name": "model.layers.51.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1789952 |
|
}, |
|
{ |
|
"name": "model.layers.51.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1800192 |
|
}, |
|
{ |
|
"name": "model.layers.52.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1810432 |
|
}, |
|
{ |
|
"name": "model.layers.52.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1824768 |
|
}, |
|
{ |
|
"name": "model.layers.52.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1835008 |
|
}, |
|
{ |
|
"name": "model.layers.53.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1845248 |
|
}, |
|
{ |
|
"name": "model.layers.53.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1859584 |
|
}, |
|
{ |
|
"name": "model.layers.53.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1869824 |
|
}, |
|
{ |
|
"name": "model.layers.54.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1880064 |
|
}, |
|
{ |
|
"name": "model.layers.54.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1894400 |
|
}, |
|
{ |
|
"name": "model.layers.54.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1904640 |
|
}, |
|
{ |
|
"name": "model.layers.55.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1914880 |
|
}, |
|
{ |
|
"name": "model.layers.55.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1929216 |
|
}, |
|
{ |
|
"name": "model.layers.55.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1939456 |
|
}, |
|
{ |
|
"name": "model.layers.56.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1949696 |
|
}, |
|
{ |
|
"name": "model.layers.56.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1964032 |
|
}, |
|
{ |
|
"name": "model.layers.56.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1974272 |
|
}, |
|
{ |
|
"name": "model.layers.57.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 1984512 |
|
}, |
|
{ |
|
"name": "model.layers.57.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 1998848 |
|
}, |
|
{ |
|
"name": "model.layers.57.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2009088 |
|
}, |
|
{ |
|
"name": "model.layers.58.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 2019328 |
|
}, |
|
{ |
|
"name": "model.layers.58.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2033664 |
|
}, |
|
{ |
|
"name": "model.layers.58.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2043904 |
|
}, |
|
{ |
|
"name": "model.layers.59.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 2054144 |
|
}, |
|
{ |
|
"name": "model.layers.59.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2068480 |
|
}, |
|
{ |
|
"name": "model.layers.59.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2078720 |
|
}, |
|
{ |
|
"name": "model.layers.60.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 2088960 |
|
}, |
|
{ |
|
"name": "model.layers.60.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2103296 |
|
}, |
|
{ |
|
"name": "model.layers.60.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2113536 |
|
}, |
|
{ |
|
"name": "model.layers.61.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 2123776 |
|
}, |
|
{ |
|
"name": "model.layers.61.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2138112 |
|
}, |
|
{ |
|
"name": "model.layers.61.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2148352 |
|
}, |
|
{ |
|
"name": "model.layers.62.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 2158592 |
|
}, |
|
{ |
|
"name": "model.layers.62.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2172928 |
|
}, |
|
{ |
|
"name": "model.layers.62.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2183168 |
|
}, |
|
{ |
|
"name": "model.layers.63.self_attn.c_attn.bias", |
|
"shape": [ |
|
7168 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 14336, |
|
"byteOffset": 2193408 |
|
}, |
|
{ |
|
"name": "model.layers.63.input_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2207744 |
|
}, |
|
{ |
|
"name": "model.layers.63.post_attention_layernorm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2217984 |
|
}, |
|
{ |
|
"name": "model.norm.weight", |
|
"shape": [ |
|
5120 |
|
], |
|
"dtype": "float16", |
|
"format": "f32-to-bf16", |
|
"nbytes": 10240, |
|
"byteOffset": 2228224 |
|
} |
|
], |
|
"md5sum": "05114a05828c85f1ce585a22b0d4a198" |
|
} |
|
] |
|
} |