{ "_name_or_path": "/opt/ml/models/DPR_with_difficult/p_encoder_1_9_1", "architectures": [ "BertEncoder" ], "attention_probs_dropout_prob": 0.1, "directionality": "bidi", "embedding_size": 768, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "position_embedding_type": "absolute", "transformers_version": "4.5.0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 42000 }