Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
Thank you for your excellent work on UForm. Are there plans to release fine-tuning scripts for the models in this repository? Such resources would be immensely helpful for adapting the models to specific tasks.
Hi,
Thank you for your excellent work on UForm. Are there plans to release fine-tuning scripts for the models in this repository? Such resources would be immensely helpful for adapting the models to specific tasks.
Thank you!