| { |
| "metadata": { |
| "total_size": 38069813248 |
| }, |
| "weight_map": { |
| "encoder.layers.0.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.0.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.0.ffn.ffn.w_out.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.0.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.0.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.0.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.0.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.0.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.0.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.ffn.ffn.w_out.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.1.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.10.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.10.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.10.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.10.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.10.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.10.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.10.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.10.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.10.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.11.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.11.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.11.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.11.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.11.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.11.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.11.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.11.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.11.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.12.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.12.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.12.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.12.ffn.layernorm_before_ffn.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.12.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.12.self_att.self_attention.attention_out.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.12.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.12.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.12.self_att.self_attention.project_v.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.ffn.layernorm_before_ffn.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.self_att.self_attention.attention_out.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.13.self_att.self_attention.project_v.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.ffn.layernorm_before_ffn.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.self_att.self_attention.attention_out.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.14.self_att.self_attention.project_v.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.15.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.15.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.15.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.15.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.15.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.15.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.15.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.15.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00013.bin", |
| "encoder.layers.15.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.self_att.self_attention.project_q.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.16.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.self_att.self_attention.project_q.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.17.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.self_att.self_attention.project_q.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.18.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.19.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.19.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.19.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.19.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.19.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00013.bin", |
| "encoder.layers.19.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.19.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.19.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.19.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.2.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.2.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.2.ffn.ffn.w_out.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.2.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.2.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.2.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.2.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.2.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.2.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.20.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.20.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.20.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.20.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.20.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.20.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.20.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.20.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.20.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.21.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.22.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.22.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.22.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.22.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.22.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.22.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.22.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.22.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.22.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00013.bin", |
| "encoder.layers.23.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.23.ffn.ffn.w_in.w_1.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.23.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.23.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.23.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.23.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.23.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.23.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.23.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.ffn.ffn.w_in.w_1.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.24.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.ffn.ffn.w_in.w_1.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.25.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.26.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.26.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.26.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.26.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.26.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.26.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.26.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.26.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.26.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00013.bin", |
| "encoder.layers.27.ffn.ffn.w_in.w_0.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.27.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.27.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.27.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.27.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.27.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.27.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.27.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.27.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.ffn.ffn.w_in.w_0.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.28.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.ffn.ffn.w_in.w_0.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.29.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.3.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.3.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.3.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.3.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.3.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.3.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.3.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.3.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.3.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00013.bin", |
| "encoder.layers.30.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.30.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.30.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.30.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.30.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.30.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.30.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.30.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.30.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00013.bin", |
| "encoder.layers.31.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.31.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.31.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.31.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.31.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.31.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.31.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.31.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.31.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.32.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.33.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.34.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.34.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.34.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.34.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.34.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.34.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.34.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.34.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00013.bin", |
| "encoder.layers.34.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.self_att.self_attention.project_k.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.35.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.self_att.self_attention.project_k.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.36.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.self_att.self_attention.project_k.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.37.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.38.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.38.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.38.ffn.ffn.w_out.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.38.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.38.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00013.bin", |
| "encoder.layers.38.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.38.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.38.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.38.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.ffn.ffn.w_out.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.self_att.layernorm_before_attention.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.39.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.4.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.4.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.4.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.4.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.4.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.4.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.4.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.4.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.4.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.40.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.40.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.40.ffn.ffn.w_out.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.40.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.40.self_att.layernorm_before_attention.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.40.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.40.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.40.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.40.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.41.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.41.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.41.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.41.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.41.self_att.layernorm_before_attention.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.41.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.41.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.41.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.41.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00013.bin", |
| "encoder.layers.42.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.42.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.42.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.42.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.42.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.42.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.42.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.42.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.42.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.43.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.44.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.45.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.45.ffn.ffn.w_in.w_1.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.45.ffn.ffn.w_out.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.45.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.45.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.45.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.45.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.45.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.45.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00013.bin", |
| "encoder.layers.46.ffn.ffn.w_in.w_0.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.46.ffn.ffn.w_in.w_1.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.46.ffn.ffn.w_out.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.46.ffn.layernorm_before_ffn.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.46.self_att.layernorm_before_attention.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.46.self_att.self_attention.attention_out.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.46.self_att.self_attention.project_k.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.46.self_att.self_attention.project_q.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.46.self_att.self_attention.project_v.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.ffn.ffn.w_in.w_0.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.ffn.ffn.w_in.w_1.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.ffn.ffn.w_out.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.ffn.layernorm_before_ffn.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.self_att.layernorm_before_attention.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.self_att.self_attention.attention_out.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.self_att.self_attention.project_k.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.self_att.self_attention.project_q.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.47.self_att.self_attention.project_v.weight": "pytorch_model-00013-of-00013.bin", |
| "encoder.layers.5.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.5.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.5.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.5.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.5.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.5.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.5.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.5.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.5.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.6.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.7.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.7.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.7.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.7.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.7.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.7.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.7.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.7.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.7.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00013.bin", |
| "encoder.layers.8.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.8.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.8.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.8.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.8.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.8.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.8.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.8.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.8.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.layers.9.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00013.bin", |
| "encoder.output_layernorm.weight": "pytorch_model-00013-of-00013.bin", |
| "input_embedding.weight": "pytorch_model-00013-of-00013.bin", |
| "position_bias.relative_attention_bias": "pytorch_model-00013-of-00013.bin", |
| "segment_embedding.weight": "pytorch_model-00013-of-00013.bin" |
| } |
| } |
|
|
