{ "_name_or_path": "bert-base-cased", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "finetuning_task": "mnli", "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "entailment", "1": "neutral", "2": "contradiction" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "contradiction": 2, "entailment": 0, "neutral": 1 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.13.0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 28996 }