Video-Text-to-Text
Transformers
Safetensors
MLX
English
molmo2
image-text-to-text
multimodal
olmo
molmo
custom_code
Instructions to use mlx-community/Molmo2-8B-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/Molmo2-8B-fp16 with Transformers:
# Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("mlx-community/Molmo2-8B-fp16", trust_remote_code=True, device_map="auto") - MLX
How to use mlx-community/Molmo2-8B-fp16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Molmo2-8B-fp16 mlx-community/Molmo2-8B-fp16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download processor_config.json from mlx-community/Molmo2-8B-fp16: direct link, hf CLI and curl.
- Browser
- Download file 635 Bytes
-
https://huggingface.co/mlx-community/Molmo2-8B-fp16/resolve/main/processor_config.json
- Command line
-
hf download hf://mlx-community/Molmo2-8B-fp16/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/mlx-community/Molmo2-8B-fp16/resolve/main/processor_config.json
635 Bytes
| { | |
| "image_processor": { | |
| "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 | |
| } | |
| }, | |
| "image_use_col_tokens": true, | |
| "processor_class": "Molmo2Processor", | |
| "use_single_crop_col_tokens": null, | |
| "use_single_crop_start_token": true | |
| } | |