| { | |
| "num_labels": 3, | |
| "architectures": [ | |
| "DebertaV2ForSequenceClassification" | |
| ], | |
| "id2label": { | |
| "0": "CONTRADICTION", | |
| "1": "NEUTRAL", | |
| "2": "ENTAILMENT" | |
| }, | |
| "label2id": { | |
| "CONTRADICTION": 0, | |
| "NEUTRAL": 1, | |
| "ENTAILMENT": 2 | |
| }, | |
| "model_type": "deberta-v2", | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 512, | |
| "relative_attention": true, | |
| "position_buckets": 256, | |
| "norm_rel_ebd": "layer_norm", | |
| "share_att_key": true, | |
| "pos_att_type": "p2c|c2p", | |
| "layer_norm_eps": 1e-7, | |
| "conv_kernel_size": 3, | |
| "conv_act": "gelu", | |
| "max_relative_positions": -1, | |
| "position_biased_input": false, | |
| "num_attention_heads": 24, | |
| "attention_head_size": 64, | |
| "num_hidden_layers": 24, | |
| "type_vocab_size": 0, | |
| "vocab_size": 128100, | |
| "pooling": { | |
| "dropout": 0, | |
| "hidden_act": "gelu" | |
| } | |
| } | |