Instructions to use nvidia/DAM-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Describe Anything
How to use nvidia/DAM-3B with Describe Anything:
# pip install git+https://github.com/NVlabs/describe-anything from huggingface_hub import snapshot_download from dam import DescribeAnythingModel snapshot_download(nvidia/DAM-3B, local_dir="checkpoints") dam = DescribeAnythingModel( model_path="checkpoints", conv_mode="v1", prompt_mode="focal_prompt", )
- Notebooks
- Google Colab
- Kaggle
Download vision_tower/preprocessor_config.json from nvidia/DAM-3B: direct link, hf CLI and curl.
- Browser
- Download file 394 Bytes
-
https://huggingface.co/nvidia/DAM-3B/resolve/refs%2Fpr%2F2/vision_tower/preprocessor_config.json
- Command line
-
hf download hf://nvidia/DAM-3B@refs/pr/2/vision_tower/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/nvidia/DAM-3B/resolve/refs%2Fpr%2F2/vision_tower/preprocessor_config.json
394 Bytes
| { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "SiglipImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "SiglipProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 384, | |
| "width": 384 | |
| } | |
| } | |