gerbejon/longcoder-html-nodes-mc-classifier-v1
03
1{2 "architectures": [3 "LongformerForSequenceClassification"4 ],5 "attention_probs_dropout_prob": 0.1,6 "attention_window": [7 1024,8 1024,9 1024,10 1024,11 1024,12 1024,13 1024,14 1024,15 1024,16 1024,17 1024,18 102419 ],20 "bos_token_id": 0,21 "classifier_dropout": null,22 "eos_token_id": 2,23 "gradient_checkpointing": false,24 "hidden_act": "gelu",25 "hidden_dropout_prob": 0.1,26 "hidden_size": 768,27 "id2label": {28 "0": "0",29 "1": "1",30 "2": "2",31 "3": "3",32 "4": "4",33 "5": "5",34 "6": "6",35 "7": "7",36 "8": "multiple"37 },38 "initializer_range": 0.02,39 "intermediate_size": 3072,40 "is_decoder_only": true,41 "label2id": {42 "0": 0,43 "1": 1,44 "2": 2,45 "3": 3,46 "4": 4,47 "5": 5,48 "6": 6,49 "7": 7,50 "multiple": 851 },52 "layer_norm_eps": 1e-05,53 "max_position_embeddings": 4098,54 "model_type": "longformer",55 "num_attention_heads": 12,56 "num_hidden_layers": 12,57 "onnx_export": false,58 "output_past": true,59 "pad_token_id": 1,60 "position_embedding_type": "absolute",61 "problem_type": "single_label_classification",62 "sep_token_id": 2,63 "torch_dtype": "float32",64 "transformers_version": "4.55.2",65 "type_vocab_size": 10,66 "use_cache": true,67 "vocab_size": 5141668}69 