---
language:
- zh
license: apache-2.0
tags:
- llava
- vlm
datasets:
- LinkSoul/Chinese-LLaVA-Vision-Instructions
---

The Chinese Baichuan2-7B-Chat VLM trained via LORA for https://arxiv.org/abs/2406.11665.

The training data used for multimodal alignment and visual instruction tuning is from [here](https://huggingface.co/datasets/LinkSoul/Chinese-LLaVA-Vision-Instructions).