{ "_name_or_path": "naver-clova-ix/donut-base", "align_long_axis": false, "architectures": [ "DonutModel" ], "decoder_layer": 4, "encoder_layer": [ 2, 2, 14, 2 ], "input_size": [ 1280, 960 ], "max_length": 768, "max_position_embeddings": 768, "model_type": "vision-encoder-decoder", "torch_dtype": "float32", "transformers_version": "4.25.1", "window_size": 10 }