ayshi/basic_distil
013
1{2 "_name_or_path": "ayshi/basic_distil",3 "activation": "gelu",4 "architectures": [5 "DistilBertForSequenceClassification"6 ],7 "attention_dropout": 0.1,8 "dim": 768,9 "dropout": 0.1,10 "hidden_dim": 3072,11 "id2label": {12 "0": "LABEL_0",13 "1": "LABEL_1",14 "2": "LABEL_2",15 "3": "LABEL_3",16 "4": "LABEL_4",17 "5": "LABEL_5"18 },19 "initializer_range": 0.02,20 "label2id": {21 "LABEL_0": 0,22 "LABEL_1": 1,23 "LABEL_2": 2,24 "LABEL_3": 3,25 "LABEL_4": 4,26 "LABEL_5": 527 },28 "max_position_embeddings": 512,29 "model_type": "distilbert",30 "n_heads": 12,31 "n_layers": 6,32 "output_past": true,33 "pad_token_id": 0,34 "qa_dropout": 0.1,35 "seq_classif_dropout": 0.2,36 "sinusoidal_pos_embds": false,37 "tie_weights_": true,38 "transformers_version": "4.34.0",39 "vocab_size": 11954740}41 