{ "_name_or_path": "xlm-roberta-base", "architectures": [ "XLMRobertaForSequenceClassification" ], "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": 768, "id2label": { "0": "Other", "1": "Information/Explanation", "2": "News", "3": "Instruction", "4": "Opinion/Argumentation", "5": "Forum", "6": "Prose/Lyrical", "7": "Legal", "8": "Promotion" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "Other": 0, "Information/Explanation": 1, "News": 2, "Instruction": 3, "Opinion/Argumentation": 4, "Forum": 5, "Prose/Lyrical": 6, "Legal": 7, "Promotion": 8 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "xlm-roberta", "num_attention_heads": 12, "num_hidden_layers": 12, "output_past": true, "pad_token_id": 1, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.20.1", "type_vocab_size": 1, "use_cache": true, "vocab_size": 250002 }