{ "activation": "gelu", "architectures": [ "DistilBertModel" ], "attention_dropout": 0.1, "dim": 2, "dropout": 0.1, "hidden_dim": 8, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 2, "n_layers": 2, "pad_token_id": 0, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "transformers_version": "4.7.0.dev0", "vocab_size": 4 }