| { | |
| "architectures": [ | |
| "DebertaV2ForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 1, | |
| "class_weights": [ | |
| 0.24696364998817444, | |
| 0.23869596421718597, | |
| 0.23614580929279327, | |
| 5.525811672210693, | |
| 0.23364955186843872, | |
| 1.0328619480133057, | |
| 0.24947232007980347, | |
| 0.2363983690738678 | |
| ], | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "coding problems", | |
| "1": "creative writing", | |
| "2": "general knowledge", | |
| "3": "history questions", | |
| "4": "math problems", | |
| "5": "other", | |
| "6": "web coding", | |
| "7": "web search required" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "coding problems": 0, | |
| "creative writing": 1, | |
| "general knowledge": 2, | |
| "history questions": 3, | |
| "math problems": 4, | |
| "other": 5, | |
| "web coding": 6, | |
| "web search required": 7 | |
| }, | |
| "layer_norm_eps": 1e-07, | |
| "legacy": true, | |
| "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, | |
| "transformers_version": "4.56.1", | |
| "type_vocab_size": 0, | |
| "vocab_size": 128100 | |
| } | |