![](https://cdn-avatars.huggingface.co/v1/production/uploads/5f1158120c833276f61f1a84/HYIF0By10WazlTdVv3xp0.jpeg)
llava-hf/llava-interleave-qwen-0.5b-hf
Image-Text-to-Text
•
Updated
•
8.32k
•
25
LLaVa models that extends the model capabilities to Multi-image, Multi-frame (videos), Multi-patch (single-image) scenarios.