Instructions to use nvidia/DAM-3B-Self-Contained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Describe Anything
How to use nvidia/DAM-3B-Self-Contained 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-Self-Contained, local_dir="checkpoints") dam = DescribeAnythingModel( model_path="checkpoints", conv_mode="v1", prompt_mode="focal_prompt", )
- Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "./checkpoints/describe_anything_v0.7.2_1ep_e2a_with_words_paug_samv2_lvisv4_mapillary_cocostuff_openimages_context_crop_constrained_blur0.5/mm_projector", | |
| "architectures": [ | |
| "MultimodalProjector" | |
| ], | |
| "mm_projector_type": "mlp_downsample", | |
| "model_type": "v2l_projector", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.2" | |
| } | |