LogischeIP/zero-shot_text_classification
013
1{2 "_name_or_path": "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli",3 "architectures": [4 "DebertaV2ForSequenceClassification"5 ],6 "attention_probs_dropout_prob": 0.1,7 "hidden_act": "gelu",8 "hidden_dropout_prob": 0.1,9 "hidden_size": 768,10 "id2label": {11 "0": "LABEL_0",12 "1": "LABEL_1",13 "2": "LABEL_2",14 "3": "LABEL_3",15 "4": "LABEL_4",16 "5": "LABEL_5",17 "6": "LABEL_6",18 "7": "LABEL_7"19 },20 "initializer_range": 0.02,21 "intermediate_size": 3072,22 "label2id": {23 "LABEL_0": 0,24 "LABEL_1": 1,25 "LABEL_2": 2,26 "LABEL_3": 3,27 "LABEL_4": 4,28 "LABEL_5": 5,29 "LABEL_6": 6,30 "LABEL_7": 731 },32 "layer_norm_eps": 1e-07,33 "max_position_embeddings": 512,34 "max_relative_positions": -1,35 "model_type": "deberta-v2",36 "norm_rel_ebd": "layer_norm",37 "num_attention_heads": 12,38 "num_hidden_layers": 12,39 "pad_token_id": 0,40 "pooler_dropout": 0,41 "pooler_hidden_act": "gelu",42 "pooler_hidden_size": 768,43 "pos_att_type": [44 "p2c",45 "c2p"46 ],47 "position_biased_input": false,48 "position_buckets": 256,49 "relative_attention": true,50 "share_att_key": true,51 "torch_dtype": "float32",52 "transformers_version": "4.35.2",53 "type_vocab_size": 0,54 "vocab_size": 12810055}56 