{ "_name_or_path": "xlm-roberta-large", "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": 1024, "id2label": { "0": "C1", "1": "C2", "2": "C3", "3": "C4", "4": "C5", "5": "C6", "6": "C7", "7": "C8", "8": "C9" }, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "C1": 0, "C2": 1, "C3": 2, "C4": 3, "C5": 4, "C6": 5, "C7": 6, "C8": 7, "C9": 8 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "xlm-roberta", "num_attention_heads": 16, "num_hidden_layers": 24, "output_past": true, "pad_token_id": 1, "position_embedding_type": "absolute", "problem_type": "multi_label_classification", "torch_dtype": "float32", "transformers_version": "4.33.1", "type_vocab_size": 1, "use_cache": true, "vocab_size": 250002 }