README.md

---
license: apache-2.0
datasets:
- tabtoyou/KoLLaVA-CC3M-Pretrain-595K
language:
- ko
tags:
- llava
---

# EEVE-LLaVA-Pretrain-2.8B
![이미지](https://cdn.donmai.us/sample/d8/91/__nagase_kotono_idoly_pride_drawn_by_sakuranoron__sample-d8915e20211fe88aba61f1c215cc32d1.jpg)
**EEVE-LLaVA-Pretrain-2.8B**  

***This model is a pretrained version of the llava multimodal projector.***  
  
**You can use this model to finetune** ***[EEVE-Korean-Instruct-2.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-Instruct-2.8B-v1.0)***  **model.**  


### Hardware
**Using 12x RTX 4090**  

### Software
**[MoE-LLaVA](https://github.com/PKU-YuanGroup/MoE-LLaVA)**