{ "architectures": [ "LongformerForSequenceClassification" ], "attention_mode": "longformer", "attention_probs_dropout_prob": 0.1, "attention_window": [ 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512 ], "bos_token_id": 0, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "All-or-Nothing", "1": "Catastrophizing", "2": "Discounting the Positive", "3": "Fortune-telling", "4": "Labeling", "5": "Mental Filter", "6": "Mind Reading", "7": "No Distortion", "8": "Overgeneralization", "9": "Personalization", "10": "Should Statements" }, "ignore_attention_mask": false, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "All-or-Nothing": 0, "Catastrophizing": 1, "Discounting the Positive": 2, "Fortune-telling": 3, "Labeling": 4, "Mental Filter": 5, "Mind Reading": 6, "No Distortion": 7, "Overgeneralization": 8, "Personalization": 9, "Should Statements": 10 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 4098, "model_type": "longformer", "num_attention_heads": 12, "num_hidden_layers": 12, "onnx_export": false, "pad_token_id": 1, "problem_type": "single_label_classification", "sep_token_id": 2, "transformers_version": "4.57.1", "type_vocab_size": 1, "vocab_size": 50265 }