| { | |
| "metadata": { | |
| "total_size": 28005029358 | |
| }, | |
| "weight_map": { | |
| "img_temperal_embedding.0": "pytorch_model-00003-of-00003.bin", | |
| "itm_head.bias": "pytorch_model-00003-of-00003.bin", | |
| "itm_head.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.lm_head.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.14.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.27.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "language_model.transformer.h.27.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.27.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.28.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.29.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.30.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.32.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.33.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.34.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.35.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.36.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.37.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.38.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.39.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin", | |
| "language_model.transformer.wpe.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_model.transformer.wte.weight": "pytorch_model-00001-of-00003.bin", | |
| "language_projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "language_projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.cls.predictions.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.cls.predictions.decoder.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.cls.predictions.decoder.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.cls.predictions.transform.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.cls.predictions.transform.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.cls.predictions.transform.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.cls.predictions.transform.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.embeddings.layernorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.embeddings.layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.0.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.1.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.10.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.11.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.2.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.3.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.4.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.5.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.6.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.7.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.8.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.attention.key.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.attention.key.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.attention.query.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.attention.query.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.attention.value.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.attention.value.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.intermediate_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.intermediate_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.output_query.LayerNorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.output_query.LayerNorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.output_query.dense.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.encoder.layer.9.output_query.dense.weight": "pytorch_model-00001-of-00003.bin", | |
| "qformer.layernorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "qformer.layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "query_tokens": "pytorch_model-00001-of-00003.bin", | |
| "temp": "pytorch_model-00001-of-00003.bin", | |
| "text_projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "text_projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.embeddings.position_embedding": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00003.bin", | |
| "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00003.bin" | |
| } | |
| } | |