pytorch_model.bin.index.json

{"metadata": {"total_size": 13724336128}, "weight_map": {"model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.fc1.weight": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.fc1.bias": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.fc2.weight": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.fc2.bias": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-1-of-32.bin", "model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-1-of-32.bin", "model.decoder.embed_tokens.weight": "pytorch_model-1-of-32.bin", "model.decoder.embed_positions.weight": "pytorch_model-1-of-32.bin", "model.decoder.final_layer_norm.weight": "pytorch_model-1-of-32.bin", "model.decoder.final_layer_norm.bias": "pytorch_model-1-of-32.bin", "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.fc1.weight": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.fc1.bias": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.fc2.weight": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.fc2.bias": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-2-of-32.bin", "model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-2-of-32.bin", "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.fc1.weight": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.fc1.bias": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.fc2.weight": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.fc2.bias": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-3-of-32.bin", "model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-3-of-32.bin", "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.fc1.weight": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.fc1.bias": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.fc2.weight": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.fc2.bias": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-4-of-32.bin", "model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-4-of-32.bin", "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.fc1.weight": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.fc1.bias": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.fc2.weight": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.fc2.bias": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-5-of-32.bin", "model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-5-of-32.bin", "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.fc1.weight": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.fc1.bias": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.fc2.weight": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.fc2.bias": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-6-of-32.bin", "model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-6-of-32.bin", "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.fc1.weight": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.fc1.bias": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.fc2.weight": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.fc2.bias": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-7-of-32.bin", "model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-7-of-32.bin", "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.fc1.weight": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.fc1.bias": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.fc2.weight": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.fc2.bias": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-8-of-32.bin", "model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-8-of-32.bin", "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.fc1.weight": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.fc1.bias": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.fc2.weight": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.fc2.bias": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-9-of-32.bin", "model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-9-of-32.bin", "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.fc1.weight": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.fc1.bias": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.fc2.weight": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.fc2.bias": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-10-of-32.bin", "model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-10-of-32.bin", "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.fc1.weight": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.fc1.bias": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.fc2.weight": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.fc2.bias": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-11-of-32.bin", "model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-11-of-32.bin", "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.fc1.weight": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.fc1.bias": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.fc2.weight": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.fc2.bias": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-12-of-32.bin", "model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-12-of-32.bin", "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.fc1.weight": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.fc1.bias": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.fc2.weight": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.fc2.bias": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-13-of-32.bin", "model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-13-of-32.bin", "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.fc1.weight": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.fc1.bias": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.fc2.weight": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.fc2.bias": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-14-of-32.bin", "model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-14-of-32.bin", "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.fc1.weight": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.fc1.bias": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.fc2.weight": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.fc2.bias": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-15-of-32.bin", "model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-15-of-32.bin", "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.fc1.weight": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.fc1.bias": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.fc2.weight": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.fc2.bias": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-16-of-32.bin", "model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-16-of-32.bin", "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.fc1.weight": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.fc1.bias": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.fc2.weight": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.fc2.bias": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-17-of-32.bin", "model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-17-of-32.bin", "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.fc1.weight": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.fc1.bias": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.fc2.weight": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.fc2.bias": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-18-of-32.bin", "model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-18-of-32.bin", "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.fc1.weight": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.fc1.bias": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.fc2.weight": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.fc2.bias": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-19-of-32.bin", "model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-19-of-32.bin", "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.fc1.weight": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.fc1.bias": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.fc2.weight": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.fc2.bias": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-20-of-32.bin", "model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-20-of-32.bin", "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.fc1.weight": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.fc1.bias": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.fc2.weight": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.fc2.bias": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-21-of-32.bin", "model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-21-of-32.bin", "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.fc1.weight": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.fc1.bias": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.fc2.weight": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.fc2.bias": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-22-of-32.bin", "model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-22-of-32.bin", "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.fc1.weight": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.fc1.bias": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.fc2.weight": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.fc2.bias": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-23-of-32.bin", "model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-23-of-32.bin", "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.fc1.weight": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.fc1.bias": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.fc2.weight": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.fc2.bias": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-24-of-32.bin", "model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-24-of-32.bin", "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.fc1.weight": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.fc1.bias": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.fc2.weight": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.fc2.bias": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-25-of-32.bin", "model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-25-of-32.bin", "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.fc1.weight": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.fc1.bias": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.fc2.weight": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.fc2.bias": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-26-of-32.bin", "model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-26-of-32.bin", "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.fc1.weight": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.fc1.bias": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.fc2.weight": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.fc2.bias": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-27-of-32.bin", "model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-27-of-32.bin", "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.fc1.weight": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.fc1.bias": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.fc2.weight": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.fc2.bias": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-28-of-32.bin", "model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-28-of-32.bin", "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.fc1.weight": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.fc1.bias": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.fc2.weight": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.fc2.bias": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-29-of-32.bin", "model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-29-of-32.bin", "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.fc1.weight": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.fc1.bias": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.fc2.weight": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.fc2.bias": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-30-of-32.bin", "model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-30-of-32.bin", "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.fc1.weight": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.fc1.bias": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.fc2.weight": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.fc2.bias": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-31-of-32.bin", "model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-31-of-32.bin", "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.fc1.weight": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.fc1.bias": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.fc2.weight": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.fc2.bias": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-32-of-32.bin", "model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-32-of-32.bin", "lm_head.weight": "pytorch_model-32-of-32.bin"}}