{ "_name_or_path": "distilroberta-base", "architectures": [ "RobertaForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "eos_token_id": 2, "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-05, "max_position_embeddings": 514, "model_type": "roberta", "num_attention_heads": 12, "num_hidden_layers": 6, "pad_token_id": 1, "position_embedding_type": "absolute", "transformers_version": "4.6.0.dev0", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50265 }