config.json
| 1 | {
|
| 2 | "_name_or_path": "microsoft/deberta-v3-large",
|
| 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": 1024,
|
| 10 | "id2label": {
|
| 11 | "0": "contradiction",
|
| 12 | "1": "entailment",
|
| 13 | "2": "neutral"
|
| 14 | },
|
| 15 | "initializer_range": 0.02,
|
| 16 | "intermediate_size": 4096,
|
| 17 | "label2id": {
|
| 18 | "contradiction": 0,
|
| 19 | "entailment": 1,
|
| 20 | "neutral": 2
|
| 21 | },
|
| 22 | "layer_norm_eps": 1e-07,
|
| 23 | "max_position_embeddings": 512,
|
| 24 | "max_relative_positions": -1,
|
| 25 | "model_type": "deberta-v2",
|
| 26 | "norm_rel_ebd": "layer_norm",
|
| 27 | "num_attention_heads": 16,
|
| 28 | "num_hidden_layers": 24,
|
| 29 | "pad_token_id": 0,
|
| 30 | "pooler_dropout": 0,
|
| 31 | "pooler_hidden_act": "gelu",
|
| 32 | "pooler_hidden_size": 1024,
|
| 33 | "pos_att_type": [
|
| 34 | "p2c",
|
| 35 | "c2p"
|
| 36 | ],
|
| 37 | "position_biased_input": false,
|
| 38 | "position_buckets": 256,
|
| 39 | "relative_attention": true,
|
| 40 | "share_att_key": true,
|
| 41 | "torch_dtype": "float32",
|
| 42 | "transformers_version": "4.11.3",
|
| 43 | "type_vocab_size": 0,
|
| 44 | "vocab_size": 128100
|
| 45 | }
|
| 46 | |