| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "BertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "classifier_dropout": null, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 128, | |
| "id2label": { | |
| "0": "not_numberwang", | |
| "1": "numberwang", | |
| "2": "not_a_number", | |
| "3": "wangernumb" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 256, | |
| "is_decoder": false, | |
| "label2id": { | |
| "not_a_number": 2, | |
| "not_numberwang": 0, | |
| "numberwang": 1, | |
| "wangernumb": 3 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "pad_token_id": 0, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.5.4", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 69 | |
| } | |