# VLM-RLAIF: Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback

## Model Summary

This Hub repository contains a HuggingFace's `transformers` implementation of VLM-RLAIF model of SNUMPR lab.

* VLM-RLAIF-7b [[HF]](https://huggingface.co/SNUMPR/vlm_rlaif_video_llava_7b): 7B RLAIF model
<!-- | Model   | Model size | Model Description | 
| ------- | ------------- |   ------------- |  
| VLM-RLAIF-7b [[HF]](https://huggingface.co/SNUMPR/vlm_rlaif_video_llava_7b) | 7B | RLAIF model
 -->