Video-Text-to-Text
Transformers
Safetensors
MLX
English
molmo2
image-text-to-text
multimodal
olmo
molmo
custom_code
8-bit precision
Instructions to use mlx-community/Molmo2-8B-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/Molmo2-8B-8bit with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mlx-community/Molmo2-8B-8bit", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("mlx-community/Molmo2-8B-8bit", trust_remote_code=True, device_map="auto") - MLX
How to use mlx-community/Molmo2-8B-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/Molmo2-8B-8bit --local-dir Molmo2-8B-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download video_preprocessor_config.json from mlx-community/Molmo2-8B-8bit: direct link, hf CLI and curl.
- Browser
- Download file 984 Bytes
-
https://huggingface.co/mlx-community/Molmo2-8B-8bit/resolve/main/video_preprocessor_config.json
- Command line
-
hf download hf://mlx-community/Molmo2-8B-8bit/video_preprocessor_config.json
-
curl -L -o video_preprocessor_config.json https://huggingface.co/mlx-community/Molmo2-8B-8bit/resolve/main/video_preprocessor_config.json
984 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_molmo2.Molmo2Processor", | |
| "AutoVideoProcessor": "video_processing_molmo2.Molmo2VideoProcessor" | |
| }, | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "device": null, | |
| "do_center_crop": null, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": true, | |
| "fps": null, | |
| "frame_sample_mode": "uniform_last_frame", | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "input_data_format": null, | |
| "max_fps": 2.0, | |
| "num_frames": 384, | |
| "pad_size": null, | |
| "patch_size": 14, | |
| "pooling_size": [ | |
| 3, | |
| 3 | |
| ], | |
| "processor_class": "Molmo2Processor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "sampling_fps": 2, | |
| "size": { | |
| "height": 378, | |
| "width": 378 | |
| }, | |
| "video_metadata": null, | |
| "video_processor_type": "Molmo2VideoProcessor" | |
| } | |