| { |
| "_name_or_path": "microsoft/deberta-v3-small", |
| "architectures": [ |
| "DebertaV2ForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "QA", |
| "1": "Summary", |
| "2": "Coding", |
| "3": "Reasoning", |
| "4": "Agentic", |
| "5": "Creative", |
| "6": "Translation", |
| "7": "Classification", |
| "8": "Extraction", |
| "9": "Long-context", |
| "10": "Fast/simple" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "Agentic": 4, |
| "Classification": 7, |
| "Coding": 2, |
| "Creative": 5, |
| "Extraction": 8, |
| "Fast/simple": 10, |
| "Long-context": 9, |
| "QA": 0, |
| "Reasoning": 3, |
| "Summary": 1, |
| "Translation": 6 |
| }, |
| "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": 6, |
| "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": "4.44.2", |
| "type_vocab_size": 0, |
| "vocab_size": 128100 |
| } |
|
|
