---
datasets:
- liuhaotian/LLaVA-Pretrain
- liuhaotian/LLaVA-Instruct-150K
pipeline_tag: visual-question-answering
---

<div align="center">
  <img src="https://github.com/InternLM/lmdeploy/assets/36994684/0cf8d00f-e86b-40ba-9b54-dc8f1bc6c8d8" width="600"/>


[![Generic badge](https://img.shields.io/badge/GitHub-%20XTuner-black.svg)](https://github.com/InternLM/xtuner)


</div>

## Model

llava-v1.5-7b-xtuner is a LLaVA model fine-tuned from [Vicuna-7B-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) and [CLIP-ViT-Large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) with [LLaVA-Pretrain](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain) and [LLaVA-Instruct](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K) by [XTuner](https://github.com/InternLM/xtuner).


## Quickstart

### Installation

```shell
pip install -U 'xtuner[deepspeed]'
```

### Chat

```shell
xtuner chat lmsys/vicuna-7b-v1.5 \
  --visual-encoder openai/clip-vit-large-patch14-336 \
  --llava xtuner/llava-v1.5-7b-xtuner \
  --prompt-template vicuna \
  --image $IMAGE_PATH
```

### Training

1. Alignment module pretraining (saved by default in `./work_dirs/`)

```shell
NPROC_PER_NODE=8 xtuner train llava_vicuna_7b_v15_clip_vit_large_p14_336_e1_gpu8_pretrain --deepspeed deepspeed_zero2
```

2. Instruction following fine-tuning (saved by default in `./work_dirs/`)

```shell
NPROC_PER_NODE=8 xtuner train llava_vicuna_7b_v15_qlora_clip_vit_large_p14_336_lora_e1_gpu8_finetune --deepspeed deepspeed_zero2
```


### MMBench Evaluation

XTuner integrates the MMBench evaluation, and you can perform evaluations with the following command!

```bash
xtuner mmbench lmsys/vicuna-7b-v1.5 \
  --visual-encoder openai/clip-vit-large-patch14-336 \
  --llava xtuner/llava-v1.5-7b-xtuner \
  --prompt-template vicuna \
  --data-path $MMBENCH_DATA_PATH \
  --work-dir $RESULT_PATH
```

After the evaluation is completed, if it's a development set, it will directly print out the results; If it's a test set, you need to submit `mmbench_result.xlsx` to the official MMBench for final evaluation to obtain precision results!

## Citation

```bibtex
@misc{2023xtuner,
    title={XTuner: A Toolkit for Efficiently Fine-tuning LLM},
    author={XTuner Contributors},
    howpublished = {\url{https://github.com/InternLM/xtuner}},
    year={2023}
}
```