llava-llama-3-8b

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

</div>

Model

llava-llama-3-8b is a LLaVA model fine-tuned from meta-llama/Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336 with LLaVA-Pretrain and LLaVA-Instruct by XTuner.

Note: This model is in XTuner LLaVA format.

Resources:

• GitHub: xtuner
• HuggingFace LLaVA format model: xtuner/llava-llama-3-8b-transformers
• Official LLaVA format model: xtuner/llava-llama-3-8b-hf

Details

Results

<div align="center"> <img src="https://github.com/InternLM/xtuner/assets/36994684/a157638c-3500-44ed-bfab-d8d8249f91bb" alt="Image" width=500" /> </div>

Quickstart

Installation

pip install 'git+https://github.com/InternLM/xtuner.git#egg=xtuner[deepspeed]'

Chat

xtuner chat xtuner/llava-llama-3-8b \
  --visual-encoder openai/clip-vit-large-patch14-336 \
  --llava xtuner/llava-llama-3-8b \
  --prompt-template llama3_chat \
  --image $IMAGE_PATH

MMBench Evaluation

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

xtuner mmbench xtuner/llava-llama-3-8b \
  --visual-encoder openai/clip-vit-large-patch14-336 \
  --llava xtuner/llava-llama-3-8b \
  --prompt-template llama3_chat \
  --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!

Reproduce

Please refer to docs.

Citation

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