{ "_num_labels": 9, "architectures": [ "RobertaForTokenClassification" ], "attention_probs_dropout_prob": 0.1, "bad_words_ids": null, "bos_token_id": 0, "decoder_start_token_id": null, "do_sample": false, "early_stopping": false, "eos_token_id": 2, "finetuning_task": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "B-PER", "1": "B-ORG", "2": "B-LOC", "3": "B-MISC", "4": "I-PER", "5": "I-ORG", "6": "I-LOC", "7": "I-MISC", "8": "O" }, "initializer_range": 0.02, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "B-LOC": 2, "B-MISC": 3, "B-ORG": 1, "B-PER": 0, "I-LOC": 6, "I-MISC": 7, "I-ORG": 5, "I-PER": 4, "O": 8 }, "layer_norm_eps": 1e-05, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 514, "min_length": 0, "model_type": "roberta", "no_repeat_ngram_size": 0, "num_attention_heads": 12, "num_beams": 1, "num_hidden_layers": 12, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_past": true, "pad_token_id": 1, "prefix": null, "pruned_heads": {}, "repetition_penalty": 1.0, "task_specific_params": null, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "torchscript": false, "type_vocab_size": 1, "use_bfloat16": false, "vocab_size": 39985 }