{ "_name_or_path": "kiddothe2b/longformer-mini-1024", "architectures": [ "LongformerForSequenceClassification" ], "attention_mode": "longformer", "attention_probs_dropout_prob": 0.1, "attention_window": [ 128, 128, 128, 128, 128, 128 ], "bos_token_id": null, "classifier_dropout": null, "cls_token_id": 101, "eos_token_id": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 256, "id2label": { "0": "NEGATIVE", "1": "POSITIVE" }, "ignore_attention_mask": false, "initializer_range": 0.02, "intermediate_size": 1024, "label2id": { "NEGATIVE": 0, "POSITIVE": 1 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 1026, "max_sentence_length": 128, "max_sentence_size": 128, "max_sentences": 8, "model_max_length": 1024, "model_type": "longformer", "num_attention_heads": 4, "num_hidden_layers": 6, "onnx_export": false, "pad_token_id": 0, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "sep_token_id": 102, "torch_dtype": "float32", "transformers_version": "4.29.2", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 }