{ "activation": "gelu", "attention_dropout": 0.1, "architectures": [ "DistilBertForSequenceClassification" ], "dim": 32, "dropout": 0.1, "hidden_act": "gelu", "hidden_dim": 37, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 4, "n_layers": 5, "pad_token_id": 0, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "transformers_version": "4.11.0.dev0", "vocab_size": 1124 }