| { | |
| "_name_or_path": "microsoft/deberta-v3-base", | |
| "architectures": [ | |
| "DebertaV2ForTokenClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "B-APL", | |
| "1": "B-CMT", | |
| "2": "B-DSC", | |
| "3": "B-MAT", | |
| "4": "B-PRO", | |
| "5": "B-SMT", | |
| "6": "B-SPL", | |
| "7": "I-APL", | |
| "8": "I-CMT", | |
| "9": "I-DSC", | |
| "10": "I-MAT", | |
| "11": "I-PRO", | |
| "12": "I-SMT", | |
| "13": "I-SPL", | |
| "14": "O" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "B-APL": 0, | |
| "B-CMT": 1, | |
| "B-DSC": 2, | |
| "B-MAT": 3, | |
| "B-PRO": 4, | |
| "B-SMT": 5, | |
| "B-SPL": 6, | |
| "I-APL": 7, | |
| "I-CMT": 8, | |
| "I-DSC": 9, | |
| "I-MAT": 10, | |
| "I-PRO": 11, | |
| "I-SMT": 12, | |
| "I-SPL": 13, | |
| "O": 14 | |
| }, | |
| "layer_norm_eps": 1e-07, | |
| "max_position_embeddings": 512, | |
| "max_relative_positions": -1, | |
| "model_type": "deberta-v2", | |
| "norm_rel_ebd": "layer_norm", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pooler_dropout": 0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 768, | |
| "pos_att_type": [ | |
| "p2c", | |
| "c2p" | |
| ], | |
| "position_biased_input": false, | |
| "position_buckets": 256, | |
| "relative_attention": true, | |
| "share_att_key": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.2", | |
| "type_vocab_size": 0, | |
| "vocab_size": 128100 | |
| } | |