Instructions to use HaochenWang/GAR-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HaochenWang/GAR-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="HaochenWang/GAR-8B", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("HaochenWang/GAR-8B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "patch_size": 14, | |
| "pooling_ratio": 2, | |
| "processor_class": "GARPerceptionLMProcessor", | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_perception_lm_fast.PerceptionLMImageProcessorFast", | |
| "AutoProcessor": "processing_gar.GARPerceptionLMProcessor" | |
| } | |
| } | |