Instructions to use xiaomoguhzz/VisionEncoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xiaomoguhzz/VisionEncoder with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("xiaomoguhzz/VisionEncoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
2 days ago
-
Add S2 20% data manifests and standalone frame cache handoff
Verified signaturePublish the current 147,718 image and 220,011 video training records, unique media lists, 64-frame cache source indices, standalone CPU frame extraction code, and usage instructions.2c547e7