{ "_name_or_path": "ehdwns1516/klue-roberta-base_sae", "architectures": [ "RobertaForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "eos_token_id": 2, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "yes/no", "1": "alternative", "2": "wh- questions", "3": "prohibitions", "4": "requirements", "5": "strong requirements" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "yes/no": 0, "alternative": 1, "wh- questions": 2, "prohibitions": 3, "requirements": 4, "strong requirements": 5 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 512, "model_type": "roberta", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "tokenizer_class": "BertTokenizer", "torch_dtype": "float32", "transformers_version": "4.9.2", "type_vocab_size": 1, "use_cache": true, "vocab_size": 32000 }