{ "_name_or_path": "klue/roberta-small", "architectures": [ "RobertaForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "classifier_dropout": null, "eos_token_id": 2, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "fragment", "1": "statement", "2": "question", "3": "command", "4": "rhetorical question", "5": "rhetorical command", "6": "intonation-depedent utterance" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "command": 3, "fragment": 0, "intonation-depedent utterance": 6, "question": 2, "rhetorical command": 5, "rhetorical question": 4, "statement": 1 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "roberta", "num_attention_heads": 12, "num_hidden_layers": 6, "pad_token_id": 1, "position_embedding_type": "absolute", "tokenizer_class": "BertTokenizer", "transformers_version": "4.11.3", "type_vocab_size": 1, "use_cache": true, "vocab_size": 32000 }