| { | |
| "_name_or_path": "microsoft/mdeberta-v3-base", | |
| "architectures": [ | |
| "DebertaV2ForTokenClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "O", | |
| "1": "B-ORG", | |
| "2": "I-ORG", | |
| "3": "B-LOC", | |
| "4": "I-LOC", | |
| "5": "B-PER", | |
| "6": "I-PER" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "B-LOC": 3, | |
| "B-ORG": 1, | |
| "B-PER": 5, | |
| "I-LOC": 4, | |
| "I-ORG": 2, | |
| "I-PER": 6, | |
| "O": 0 | |
| }, | |
| "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": "4.12.5", | |
| "type_vocab_size": 0, | |
| "vocab_size": 251000 | |
| } | |