{ "_name_or_path": "roberta-large", "architectures": [ "RobertaForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "classifier_dropout": null, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6", "7": "LABEL_7" }, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2, "LABEL_3": 3, "LABEL_4": 4, "LABEL_5": 5, "LABEL_6": 6, "LABEL_7": 7 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "roberta", "num_attention_heads": 16, "num_hidden_layers": 24, "pad_token_id": 1, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.44.1", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50265 }