Instructions to use somusan/molmo2-vqa-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use somusan/molmo2-vqa-lora with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("somusan/molmo2-vqa-lora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download final_adapter/preprocessor_config.json from somusan/molmo2-vqa-lora: direct link, hf CLI and curl.
- Browser
- Download file 555 Bytes
-
https://huggingface.co/somusan/molmo2-vqa-lora/resolve/main/final_adapter/preprocessor_config.json
- Command line
-
hf download hf://somusan/molmo2-vqa-lora/final_adapter/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/somusan/molmo2-vqa-lora/resolve/main/final_adapter/preprocessor_config.json
555 Bytes
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_molmo2.Molmo2ImageProcessor", | |
| "AutoProcessor": "processing_molmo2.Molmo2Processor" | |
| }, | |
| "do_convert_rgb": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Molmo2ImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_crops": 8, | |
| "overlap_margins": [ | |
| 4, | |
| 4 | |
| ], | |
| "patch_size": 14, | |
| "pooling_size": [ | |
| 2, | |
| 2 | |
| ], | |
| "processor_class": "Molmo2Processor", | |
| "resample": 2, | |
| "size": { | |
| "height": 378, | |
| "width": 378 | |
| } | |
| } | |