| { | |
| "model_name": "SenseNova-Vision-7B-MoT", | |
| "base_model": "BAGEL-7B-MoT", | |
| "model_family": "unified_multimodal_generation", | |
| "parameter_size": "7B", | |
| "modality": ["text", "image"], | |
| "capabilities": [ | |
| "visual understanding", | |
| "image generation", | |
| "image editing", | |
| "dense perception", | |
| "segmentation", | |
| "depth estimation", | |
| "normal estimation", | |
| "multi-view geometry" | |
| ], | |
| "load_with_transformers_automodel": false, | |
| "official_inference_code": "https://github.com/OpenSenseNova/SenseNova-Vision", | |
| "note": "This file is provided for project-level metadata only. The model cannot be loaded directly with transformers.AutoModel.from_pretrained." | |
| } |