Instructions to use tiny-random/lfm3-omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tiny-random/lfm3-omni with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("tiny-random/lfm3-omni", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download video_preprocessor_config.json from tiny-random/lfm3-omni: direct link, hf CLI and curl.
- Browser
- Download file 706 Bytes
-
https://huggingface.co/tiny-random/lfm3-omni/resolve/main/video_preprocessor_config.json
- Command line
-
hf download hf://tiny-random/lfm3-omni/video_preprocessor_config.json
-
curl -L -o video_preprocessor_config.json https://huggingface.co/tiny-random/lfm3-omni/resolve/main/video_preprocessor_config.json
706 Bytes
| { | |
| "cap_pixels_per_frame": false, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": true, | |
| "fps": 2.0, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_frames": 384, | |
| "max_video_tokens": 768, | |
| "merge_size": 2, | |
| "min_frames": 4, | |
| "patch_size": 16, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "longest_edge": 25165824, | |
| "shortest_edge": 4096 | |
| }, | |
| "temporal_patch_size": 2, | |
| "video_processor_type": "Lfm3VlVideoProcessor", | |
| "auto_map": { | |
| "AutoVideoProcessor": "video_processing_lfm3_vl.Lfm3VlVideoProcessor" | |
| } | |
| } | |