|
{ |
|
"metadata": { |
|
"total_size": 27686882816 |
|
}, |
|
"weight_map": { |
|
"lm_head.weight": "pytorch_model-00002-of-00034.bin", |
|
"transformer.h.0.input_layernorm.bias": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.0.input_layernorm.weight": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.1.input_layernorm.bias": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.1.input_layernorm.weight": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00034.bin", |
|
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00034.bin", |
|
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00003-of-00034.bin", |
|
"transformer.h.10.input_layernorm.bias": "pytorch_model-00012-of-00034.bin", |
|
"transformer.h.10.input_layernorm.weight": "pytorch_model-00012-of-00034.bin", |
|
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00034.bin", |
|
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00034.bin", |
|
"transformer.h.10.self_attention.dense.weight": "pytorch_model-00012-of-00034.bin", |
|
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00012-of-00034.bin", |
|
"transformer.h.11.input_layernorm.bias": "pytorch_model-00013-of-00034.bin", |
|
"transformer.h.11.input_layernorm.weight": "pytorch_model-00013-of-00034.bin", |
|
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00034.bin", |
|
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00034.bin", |
|
"transformer.h.11.self_attention.dense.weight": "pytorch_model-00013-of-00034.bin", |
|
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00013-of-00034.bin", |
|
"transformer.h.12.input_layernorm.bias": "pytorch_model-00014-of-00034.bin", |
|
"transformer.h.12.input_layernorm.weight": "pytorch_model-00014-of-00034.bin", |
|
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00034.bin", |
|
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00034.bin", |
|
"transformer.h.12.self_attention.dense.weight": "pytorch_model-00014-of-00034.bin", |
|
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00014-of-00034.bin", |
|
"transformer.h.13.input_layernorm.bias": "pytorch_model-00015-of-00034.bin", |
|
"transformer.h.13.input_layernorm.weight": "pytorch_model-00015-of-00034.bin", |
|
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00016-of-00034.bin", |
|
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00016-of-00034.bin", |
|
"transformer.h.13.self_attention.dense.weight": "pytorch_model-00015-of-00034.bin", |
|
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00015-of-00034.bin", |
|
"transformer.h.14.input_layernorm.bias": "pytorch_model-00016-of-00034.bin", |
|
"transformer.h.14.input_layernorm.weight": "pytorch_model-00016-of-00034.bin", |
|
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00017-of-00034.bin", |
|
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00017-of-00034.bin", |
|
"transformer.h.14.self_attention.dense.weight": "pytorch_model-00016-of-00034.bin", |
|
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00016-of-00034.bin", |
|
"transformer.h.15.input_layernorm.bias": "pytorch_model-00017-of-00034.bin", |
|
"transformer.h.15.input_layernorm.weight": "pytorch_model-00017-of-00034.bin", |
|
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00018-of-00034.bin", |
|
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00018-of-00034.bin", |
|
"transformer.h.15.self_attention.dense.weight": "pytorch_model-00017-of-00034.bin", |
|
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00017-of-00034.bin", |
|
"transformer.h.16.input_layernorm.bias": "pytorch_model-00018-of-00034.bin", |
|
"transformer.h.16.input_layernorm.weight": "pytorch_model-00018-of-00034.bin", |
|
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00019-of-00034.bin", |
|
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00019-of-00034.bin", |
|
"transformer.h.16.self_attention.dense.weight": "pytorch_model-00018-of-00034.bin", |
|
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00018-of-00034.bin", |
|
"transformer.h.17.input_layernorm.bias": "pytorch_model-00019-of-00034.bin", |
|
"transformer.h.17.input_layernorm.weight": "pytorch_model-00019-of-00034.bin", |
|
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00020-of-00034.bin", |
|
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00020-of-00034.bin", |
|
"transformer.h.17.self_attention.dense.weight": "pytorch_model-00019-of-00034.bin", |
|
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00019-of-00034.bin", |
|
"transformer.h.18.input_layernorm.bias": "pytorch_model-00020-of-00034.bin", |
|
"transformer.h.18.input_layernorm.weight": "pytorch_model-00020-of-00034.bin", |
|
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00021-of-00034.bin", |
|
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00021-of-00034.bin", |
|
"transformer.h.18.self_attention.dense.weight": "pytorch_model-00020-of-00034.bin", |
|
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00020-of-00034.bin", |
|
"transformer.h.19.input_layernorm.bias": "pytorch_model-00021-of-00034.bin", |
|
"transformer.h.19.input_layernorm.weight": "pytorch_model-00021-of-00034.bin", |
|
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00022-of-00034.bin", |
|
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00022-of-00034.bin", |
|
"transformer.h.19.self_attention.dense.weight": "pytorch_model-00021-of-00034.bin", |
|
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00021-of-00034.bin", |
|
"transformer.h.2.input_layernorm.bias": "pytorch_model-00004-of-00034.bin", |
|
"transformer.h.2.input_layernorm.weight": "pytorch_model-00004-of-00034.bin", |
|
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00034.bin", |
|
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00034.bin", |
|
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00004-of-00034.bin", |
|
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00004-of-00034.bin", |
|
"transformer.h.20.input_layernorm.bias": "pytorch_model-00022-of-00034.bin", |
|
"transformer.h.20.input_layernorm.weight": "pytorch_model-00022-of-00034.bin", |
|
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00023-of-00034.bin", |
|
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00023-of-00034.bin", |
|
"transformer.h.20.self_attention.dense.weight": "pytorch_model-00022-of-00034.bin", |
|
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00022-of-00034.bin", |
|
"transformer.h.21.input_layernorm.bias": "pytorch_model-00023-of-00034.bin", |
|
"transformer.h.21.input_layernorm.weight": "pytorch_model-00023-of-00034.bin", |
|
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00024-of-00034.bin", |
|
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00024-of-00034.bin", |
|
"transformer.h.21.self_attention.dense.weight": "pytorch_model-00023-of-00034.bin", |
|
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00023-of-00034.bin", |
|
"transformer.h.22.input_layernorm.bias": "pytorch_model-00024-of-00034.bin", |
|
"transformer.h.22.input_layernorm.weight": "pytorch_model-00024-of-00034.bin", |
|
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00025-of-00034.bin", |
|
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00025-of-00034.bin", |
|
"transformer.h.22.self_attention.dense.weight": "pytorch_model-00024-of-00034.bin", |
|
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00024-of-00034.bin", |
|
"transformer.h.23.input_layernorm.bias": "pytorch_model-00025-of-00034.bin", |
|
"transformer.h.23.input_layernorm.weight": "pytorch_model-00025-of-00034.bin", |
|
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00026-of-00034.bin", |
|
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00026-of-00034.bin", |
|
"transformer.h.23.self_attention.dense.weight": "pytorch_model-00025-of-00034.bin", |
|
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00025-of-00034.bin", |
|
"transformer.h.24.input_layernorm.bias": "pytorch_model-00026-of-00034.bin", |
|
"transformer.h.24.input_layernorm.weight": "pytorch_model-00026-of-00034.bin", |
|
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00027-of-00034.bin", |
|
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00027-of-00034.bin", |
|
"transformer.h.24.self_attention.dense.weight": "pytorch_model-00026-of-00034.bin", |
|
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00026-of-00034.bin", |
|
"transformer.h.25.input_layernorm.bias": "pytorch_model-00027-of-00034.bin", |
|
"transformer.h.25.input_layernorm.weight": "pytorch_model-00027-of-00034.bin", |
|
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00028-of-00034.bin", |
|
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00028-of-00034.bin", |
|
"transformer.h.25.self_attention.dense.weight": "pytorch_model-00027-of-00034.bin", |
|
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00027-of-00034.bin", |
|
"transformer.h.26.input_layernorm.bias": "pytorch_model-00028-of-00034.bin", |
|
"transformer.h.26.input_layernorm.weight": "pytorch_model-00028-of-00034.bin", |
|
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00029-of-00034.bin", |
|
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00029-of-00034.bin", |
|
"transformer.h.26.self_attention.dense.weight": "pytorch_model-00028-of-00034.bin", |
|
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00028-of-00034.bin", |
|
"transformer.h.27.input_layernorm.bias": "pytorch_model-00029-of-00034.bin", |
|
"transformer.h.27.input_layernorm.weight": "pytorch_model-00029-of-00034.bin", |
|
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00030-of-00034.bin", |
|
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00030-of-00034.bin", |
|
"transformer.h.27.self_attention.dense.weight": "pytorch_model-00029-of-00034.bin", |
|
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00029-of-00034.bin", |
|
"transformer.h.28.input_layernorm.bias": "pytorch_model-00030-of-00034.bin", |
|
"transformer.h.28.input_layernorm.weight": "pytorch_model-00030-of-00034.bin", |
|
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00031-of-00034.bin", |
|
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00031-of-00034.bin", |
|
"transformer.h.28.self_attention.dense.weight": "pytorch_model-00030-of-00034.bin", |
|
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00030-of-00034.bin", |
|
"transformer.h.29.input_layernorm.bias": "pytorch_model-00031-of-00034.bin", |
|
"transformer.h.29.input_layernorm.weight": "pytorch_model-00031-of-00034.bin", |
|
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00032-of-00034.bin", |
|
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00032-of-00034.bin", |
|
"transformer.h.29.self_attention.dense.weight": "pytorch_model-00031-of-00034.bin", |
|
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00031-of-00034.bin", |
|
"transformer.h.3.input_layernorm.bias": "pytorch_model-00005-of-00034.bin", |
|
"transformer.h.3.input_layernorm.weight": "pytorch_model-00005-of-00034.bin", |
|
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00034.bin", |
|
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00034.bin", |
|
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00005-of-00034.bin", |
|
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00005-of-00034.bin", |
|
"transformer.h.30.input_layernorm.bias": "pytorch_model-00032-of-00034.bin", |
|
"transformer.h.30.input_layernorm.weight": "pytorch_model-00032-of-00034.bin", |
|
"transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00033-of-00034.bin", |
|
"transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00033-of-00034.bin", |
|
"transformer.h.30.self_attention.dense.weight": "pytorch_model-00032-of-00034.bin", |
|
"transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00032-of-00034.bin", |
|
"transformer.h.31.input_layernorm.bias": "pytorch_model-00033-of-00034.bin", |
|
"transformer.h.31.input_layernorm.weight": "pytorch_model-00033-of-00034.bin", |
|
"transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00034-of-00034.bin", |
|
"transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00034-of-00034.bin", |
|
"transformer.h.31.self_attention.dense.weight": "pytorch_model-00033-of-00034.bin", |
|
"transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00033-of-00034.bin", |
|
"transformer.h.4.input_layernorm.bias": "pytorch_model-00006-of-00034.bin", |
|
"transformer.h.4.input_layernorm.weight": "pytorch_model-00006-of-00034.bin", |
|
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00034.bin", |
|
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00034.bin", |
|
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00006-of-00034.bin", |
|
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00006-of-00034.bin", |
|
"transformer.h.5.input_layernorm.bias": "pytorch_model-00007-of-00034.bin", |
|
"transformer.h.5.input_layernorm.weight": "pytorch_model-00007-of-00034.bin", |
|
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00034.bin", |
|
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00034.bin", |
|
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00007-of-00034.bin", |
|
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00007-of-00034.bin", |
|
"transformer.h.6.input_layernorm.bias": "pytorch_model-00008-of-00034.bin", |
|
"transformer.h.6.input_layernorm.weight": "pytorch_model-00008-of-00034.bin", |
|
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00034.bin", |
|
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00034.bin", |
|
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00008-of-00034.bin", |
|
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00008-of-00034.bin", |
|
"transformer.h.7.input_layernorm.bias": "pytorch_model-00009-of-00034.bin", |
|
"transformer.h.7.input_layernorm.weight": "pytorch_model-00009-of-00034.bin", |
|
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00034.bin", |
|
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00034.bin", |
|
"transformer.h.7.self_attention.dense.weight": "pytorch_model-00009-of-00034.bin", |
|
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00009-of-00034.bin", |
|
"transformer.h.8.input_layernorm.bias": "pytorch_model-00010-of-00034.bin", |
|
"transformer.h.8.input_layernorm.weight": "pytorch_model-00010-of-00034.bin", |
|
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00034.bin", |
|
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00034.bin", |
|
"transformer.h.8.self_attention.dense.weight": "pytorch_model-00010-of-00034.bin", |
|
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00010-of-00034.bin", |
|
"transformer.h.9.input_layernorm.bias": "pytorch_model-00011-of-00034.bin", |
|
"transformer.h.9.input_layernorm.weight": "pytorch_model-00011-of-00034.bin", |
|
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00034.bin", |
|
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00034.bin", |
|
"transformer.h.9.self_attention.dense.weight": "pytorch_model-00011-of-00034.bin", |
|
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00011-of-00034.bin", |
|
"transformer.ln_f.bias": "pytorch_model-00034-of-00034.bin", |
|
"transformer.ln_f.weight": "pytorch_model-00034-of-00034.bin", |
|
"transformer.word_embeddings.weight": "pytorch_model-00002-of-00034.bin" |
|
} |
|
} |
|
|