{ "_name_or_path": "xlm-roberta-base", "architectures": [ "XLMRobertaForTokenClassificaton" ], "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": "O", "1": "B-PER", "2": "I-PER", "3": "B-ORG", "4": "I-ORG", "5": "B-LOC", "6": "I-LOC" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "B-LOC": 5, "B-ORG": 3, "B-PER": 1, "I-LOC": 6, "I-ORG": 4, "I-PER": 2, "O": 0 }, "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", "torch_dtype": "float32", "transformers_version": "4.37.1", "type_vocab_size": 1, "use_cache": true, "vocab_size": 250002 }