| { |
| "architectures": [ |
| "DebertaForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "CONTRADICTION", |
| "1": "NEUTRAL", |
| "2": "ENTAILMENT" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "label2id": { |
| "CONTRADICTION": 0, |
| "ENTAILMENT": 2, |
| "NEUTRAL": 1 |
| }, |
| "layer_norm_eps": 1e-07, |
| "max_position_embeddings": 512, |
| "max_relative_positions": -1, |
| "model_type": "deberta", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 48, |
| "pad_token_id": 0, |
| "pooler_dropout": 0, |
| "pooler_hidden_act": "gelu", |
| "pooler_hidden_size": 1024, |
| "pooling": { |
| "dropout": 0, |
| "hidden_act": "gelu" |
| }, |
| "pos_att_type": [ |
| "c2p", |
| "p2c" |
| ], |
| "position_biased_input": false, |
| "relative_attention": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.26.1", |
| "type_vocab_size": 0, |
| "vocab_size": 50265 |
| } |
|
|
