The folder includes the implementation of LLaVolta for Efficient Large Language and Vision Assistant.

@inproceedings{chen2024efficient,
  title={Efficient large multi-modal models via visual context compression},
  author={Chen, Jieneng and Ye, Luoxin and He, Ju and Wang, Zhao-Yang and Khashabi, Daniel and Yuille, Alan},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year={2024}
}

Note: code is developed based on Ubuntu 20.04/22.04. CUDA=12.1 Our code is developed based on LLaVA, the installation is very similar to original repo of LLaVA:

1. Clone this repository and navigate to LLaVA folder

git clone https://github.com/Beckschen/LLaVolta
cd LLaVolta

2. Install Package

conda create -n llavolta python=3.10 -y
conda activate llavolta
pip install --upgrade pip 
pip install -e .

3. Install additional packages for training cases

pip install -e ".[train]"
pip install flash-attn --no-build-isolation --no-cache-dir
cd llava/eval
tar xvf table.tar
cd ../..

1. Download the training data for both pretraining and fine-tuning from the original LLaVA repository.
2. Set the necessary path variables: ROOT_DATA, ROOT_WEIGHT, and ROOT_LOG (optional).
3. Begin training using the scripts. We provide four examples: 4stage, heavy_compression, light_compression, and reproduce.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/train-$NAME.sh

Running scripts under scripts/v1_5/eval/$NAME, where NAME is the name of checkpoint's name. We provide four example: 4stage, heavy_compression, light_compression, reproduce.

For all scripts we provided, please first fill up necessary path variables: ROOT_DATA, ROOT_WEIGHT, ROOT_LOG(optional)

1. Download test2015 and put it under $ROOT_DATA/eval/vqav2.
2. Multi-GPU inference.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/vqav2.sh

3. Submit the results to the evaluation server.

1. Download the data and evaluation scripts following the official instructions and put under $ROOT_DATA/eval/gqa/data. You may need to modify eval.py as this due to the missing assets in the GQA v1.2 release.
2. Multi-GPU inference.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/gqa.sh

1. Download test.json and extract test.zip to test. Put them under $ROOT_DATA/eval/vizwiz.
2. Single-GPU inference.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/vizwiz.sh

3. Submit the results to the evaluation server: $ROOT_DATA/eval/vizwiz/answers_upload.

1. Under $ROOT_DATA/eval/scienceqa, download images, pid_splits.json, problems.json from the data/scienceqa folder of the ScienceQA repo.
2. Single-GPU inference and evaluate.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/sqa.sh

1. Download TextVQA_0.5.1_val.json and images and extract to $ROOT_DATA/eval/textvqa.
2. Single-GPU inference and evaluate.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/textvqa.sh

1. Download coco from POPE and put under $ROOT_DATA/eval/pope.
2. Single-GPU inference and evaluate.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/pope.sh

1. Download the data following the official instructions here.
2. Downloaded images to MME_Benchmark_release_version.
3. put the official eval_tool and MME_Benchmark_release_version under $ROOT_DATA/eval/MME.
4. Single-GPU inference and evaluate.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/mme.sh

1. Download mmbench_dev_20230712.tsv and put under $ROOT_DATA/eval/mmbench.
2. Single-GPU inference.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/mmbench.sh

3. Submit the results to the evaluation server: $ROOT_DATA/eval/mmbench/answers_upload/mmbench_dev_20230712.

1. Download mmbench_dev_cn_20231003.tsv and put under $ROOT_DATA/eval/mmbench.
2. Single-GPU inference.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/mmbench_cn.sh

3. Submit the results to the evaluation server: $ROOT_DATA/eval/mmbench/answers_upload/mmbench_dev_cn_20231003.

1. Following the official instructions to download the images and the videos. Put images under $DATA_ROOT/eval/seed_bench/SEED-Bench-image. Note that we only use image subset to evaluate LLaVolta
2. Multiple-GPU inference and evaluate.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/seed.sh

1. Extract contents of llava-bench-in-the-wild to $ROOT_DATA/eval/llava-bench-in-the-wild.
2. Single-GPU inference and evaluate.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/llavabench.sh

1. Extract mm-vet.zip to $ROOT_DATA/eval/mmvet.
2. Single-GPU inference.

NAME=4stage # Option: {heavy-compression, light-compression, reproduce}
bash scripts/v1_5/eval/$NAME/mmvet.sh

3. Evaluate the predictions in $ROOT_DATA/eval/mmvet/results using the official jupyter notebook.

@inproceedings{chen2024efficient,
  title={Efficient large multi-modal models via visual context compression},
  author={Chen, Jieneng and Ye, Luoxin and He, Ju and Wang, Zhao-Yang and Khashabi, Daniel and Yuille, Alan},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year={2024}
}

• LLaVA
• Vicuna

Luoxin Ye (@feiyu12138) is the primary contributor to the codebase. We have archived the project here, in order to maintain a clean and organized code style.