Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
qnguyen3Β 
posted an update Apr 10
Post
5048
πŸŽ‰ Introducing nanoLLaVA, a powerful multimodal AI model that packs the capabilities of a 1B parameter vision language model into just 5GB of VRAM. πŸš€ This makes it an ideal choice for edge devices, bringing cutting-edge visual understanding and generation to your devices like never before. πŸ“±πŸ’»

Model: qnguyen3/nanoLLaVA πŸ”
Spaces: qnguyen3/nanoLLaVA (thanks to @merve )

Under the hood, nanoLLaVA is based on the powerful vilm/Quyen-SE-v0.1 (my Qwen1.5-0.5B finetune) and Google's impressive google/siglip-so400m-patch14-384. 🧠 The model is trained using a data-centric approach to ensure optimal performance. πŸ“Š

In the spirit of transparency and collaboration, all code and model weights are open-sourced under the Apache 2.0 license. 🀝

Excited to read the final paper! I hope this model starts a trend where MM-LLMs are getting more efficient and portable. Exciting opportunities for researchers with not a lot of compute :)