README.md

---
tags:
- image-text-to-text
- llava
- multimodal
- vision-language
---

# llava_7b_12_32

Model weights from `lbasile/llava_7b_12_32` ported to the `llava-hf/llava-1.5-7b-hf` architecture to provide a standardized chat template and processor configuration.