Instructions to use ravilution/MolmoWeb-8B-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use ravilution/MolmoWeb-8B-8bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("ravilution/MolmoWeb-8B-8bit") config = load_config("ravilution/MolmoWeb-8B-8bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Refresh: vLLM/HF compatibility patches (EOS, tokenizer regex, transformers_version)
342c6c9 verified | { | |
| "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 | |
| } | |
| } | |