{ "_name_or_path": "semaj83/scibert_finetuned_ctmatch", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "not_relevant", "1": "partially_relevant", "2": "relevant" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "not_relevant": "0", "partially_relevant": "1", "relevant": "2" }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "pruned_heads": { "0": [ 0, 1, 7 ], "1": [ 11, 10, 3 ], "2": [ 1, 3, 7, 9, 11 ], "3": [ 4 ], "4": [], "5": [ 0, 1 ], "6": [], "7": [ 7 ], "8": [], "9": [], "10": [], "11": [] }, "torch_dtype": "float32", "transformers_version": "4.29.2", "type_vocab_size": 2, "use_cache": true, "vocab_size": 31090 }