{ "activation": "gelu", "architectures": [ "DistilBertForSequenceClassification" ], "attention_dropout": 0.1, "cls_token_id": 226, "dim": 256, "dropout": 0.1, "hidden_dim": 1024, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 4, "n_layers": 4, "pad_token_id": 4992, "problem_type": "single_label_classification", "qa_dropout": 0.1, "sep_token_id": 1815, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "tie_weights_": true, "torch_dtype": "float32", "transformers_version": "4.51.3", "vocab_size": 30522 }