{ "metadata": { "total_size": 30060162048 }, "weight_map": { "lm_head.weight": "pytorch_model-00004-of-00004.bin", "model.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.0.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.1.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.10.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.11.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.12.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.13.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.14.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.15.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.16.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.17.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.18.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.19.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.2.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.20.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.21.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.22.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.23.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.24.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.25.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.26.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.27.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.28.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.29.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.3.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.30.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.self_attention.key_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.self_attention.key_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.self_attention.query_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.self_attention.query_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.self_attention.value_proj.bias": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.31.self_attention.value_proj.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", "model.encoder.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.32.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.33.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.34.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.35.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.36.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.37.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.38.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.39.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.4.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.40.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.40.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.41.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.42.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.43.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.44.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.45.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.46.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.self_attention.key_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.self_attention.key_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.self_attention.query_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.self_attention.query_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.self_attention.value_proj.bias": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.47.self_attention.value_proj.weight": "pytorch_model-00003-of-00004.bin", "model.encoder.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.5.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.6.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.7.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.8.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.self_attention.key_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.self_attention.key_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.self_attention.query_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.self_attention.query_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.self_attention.value_proj.bias": "pytorch_model-00001-of-00004.bin", "model.encoder.layers.9.self_attention.value_proj.weight": "pytorch_model-00001-of-00004.bin", "model.encoder.ln_f.weight": "pytorch_model-00003-of-00004.bin", "model.word_embeddings.weight": "pytorch_model-00001-of-00004.bin" } }