| { | |
| "_name_or_path": "microsoft/deberta-v3-xsmall", | |
| "architectures": [ | |
| "DebertaV2ForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 384, | |
| "id2label": { | |
| "0": "python-3.x", | |
| "1": "numpy", | |
| "2": "dictionary", | |
| "3": "matplotlib", | |
| "4": "pandas", | |
| "5": "python-2.7", | |
| "6": "regex", | |
| "7": "list", | |
| "8": "django", | |
| "9": "string" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "label2id": { | |
| "dictionary": 2, | |
| "django": 8, | |
| "list": 7, | |
| "matplotlib": 3, | |
| "numpy": 1, | |
| "pandas": 4, | |
| "python-2.7": 5, | |
| "python-3.x": 0, | |
| "regex": 6, | |
| "string": 9 | |
| }, | |
| "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": 6, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pooler_dropout": 0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 384, | |
| "pos_att_type": [ | |
| "p2c", | |
| "c2p" | |
| ], | |
| "position_biased_input": false, | |
| "position_buckets": 256, | |
| "problem_type": "multi_label_classification", | |
| "relative_attention": true, | |
| "share_att_key": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.45.1", | |
| "type_vocab_size": 0, | |
| "vocab_size": 128100 | |
| } | |