Visual instruction tuning towards large language and vision models with GPT-4 level capabilities.

[Project Page] [Paper] [Demo] [Data] [Model]

Visual Instruction Tuning
Haotian Liu*, Chunyuan Li*, Qingyang Wu, Yong Jae Lee (*Equal Contribution)

Generated by GLIGEN via "a cute lava llama with glasses" and box prompt

• [6/1] 🔥 We released LLaVA-Med: Large Language and Vision Assistant for Biomedicine, a step towards building biomedical domain large language and vision models with GPT-4 level capabilities. Checkout the paper and page.
• [5/13] 🔥 Interested in quantifying the emerged zero-shot OCR performance of LLaVA and open-sourced LMM? Please check out the paper "On the Hidden Mystery of OCR in Large Multimodal Models", where LLaVA consistently outperforms miniGPT4 on 17 out of 18 datasets, despite LlaVA being trained with an order of magnitude smaller training data.
• [5/6] 🔥 We are releasing LLaVA-Lighting-MPT-7B-preview, based on MPT-7B-Chat! See here for more details.
• [5/2] 🔥 We are releasing LLaVA-Lighting! Train a lite, multimodal GPT-4 with just $40 in 3 hours! See here for more details.
• [5/2] We upgrade LLaVA package to v0.1 to support Vicuna v0 and v1 checkpoints, please upgrade following instructions here.
• [4/30] Our checkpoint with Vicuna-7b-v0 has been released here! This checkpoint is more accessible and device friendly. Stay tuned for a major upgrade next week!
• [4/27] Thanks to the community effort, LLaVA-13B with 4-bit quantization allows you to run on a GPU with as few as 12GB VRAM! Try it out here.
• [4/17] 🔥 We released LLaVA: Large Language and Vision Assistant. We propose visual instruction tuning, towards building large language and vision models with GPT-4 level capabilities. Checkout the paper and demo.

Usage and License Notices: The data, code and checkpoint is intended and licensed for research use only. They are also restricted to uses that follow the license agreement of LLaMA, Vicuna and GPT-4. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.

• Data Download
• Install
• LLaVA Weights
• Serving
• Evaluation
• Fine-tuning

To download our langauge-image multimodal instruction-folllowing dataset LLaVA-Instruct-150K, please run the following script:

sh download_data.sh

The pretraining dataset used in this release is a subset of CC-3M dataset, filtered with a more balanced concept coverage distribution. Please see here for a detailed description on the dataset structure and how to download the images.

If you already have CC-3M dataset on your disk, the image names follow this format: GCC_train_000000000.jpg. You may edit the image field correspondingly if necessary.

Important notice: Upon the request from the community, as ~15% images of the original CC-3M dataset are no longer accessible, we upload images.zip for better reproducing our work in research community. It must not be used for any other purposes. The use of these images must comply with the CC-3M license. This may be taken down at any time when requested by the original CC-3M dataset owner or owners of the referenced images.

We provide our prompts and few-shot samples for GPT-4 queries, to better facilitate research in this domain. Please check out the prompts folder for three kinds of questions: conversation, detail description, and complex reasoning.

They are organized in a format of system_message.txt for system message, pairs of abc_caps.txt for few-shot sample user input, and abc_conv.txt for few-shot sample reference output.

Note that you may find them in different format. For example, conversation is in jsonl, and detail description is answer-only. The selected format in our preliminary experiments work slightly better than a limited set of alternatives that we tried: jsonl, more natural format, answer-only. If interested, you may try other variants or conduct more careful study in this. Contributions are welcomed!

1. Clone this repository and navigate to LLaVA folder

git clone https://github.com/haotian-liu/LLaVA.git
cd LLaVA

2. Install Package

conda create -n llava python=3.10 -y
conda activate llava
pip install --upgrade pip  # enable PEP 660 support
pip install -e .

NOTE: [Update 4/30/23] We have successfully moved LLaVA framework to this repo, without the need of a special transformers modified by us. If you install our repo before 4/30/23, please reinstall transformers following the instructions here.

3. Install additional packages for training cases

pip install ninja
pip install flash-attn==1.0.2

NOTE: If you install our package before 4/30/23, please make sure to execute the command below to correctly upgrade to v0.1. You may try a clean install as well.

git pull
pip uninstall transformers
pip install git+https://github.com/huggingface/transformers@cae78c46
pip install -e .

We release LLaVA weights as delta weights to comply with the LLaMA model license. You can add our delta to the original LLaMA weights to obtain the LLaVA weights.

Instructions:

1. Get the original LLaMA weights in the huggingface format by following the instructions here.
2. Use the following scripts to get LLaVA weights by applying our delta (13b-v0, 7b-v0, lightning-7B-v1-1). It will automatically download delta weights from our Hugging Face account.

This conversion command needs around 60 GB of CPU RAM.

python3 -m llava.model.apply_delta \
    --base /path/to/llama-13b \
    --target /output/path/to/LLaVA-13B-v0 \
    --delta liuhaotian/LLaVA-13b-delta-v0

This conversion command needs around 30 GB of CPU RAM.

python3 -m llava.model.apply_delta \
    --base /path/to/llama-7b \
    --target /output/path/to/LLaVA-7B-v0 \
    --delta liuhaotian/LLaVA-7b-delta-v0

The initial release is pretrained on LLaVA-filtered CC3M 595K with 1 epoch. The pretrained weights are released here.

You may perform instruction tuning on our pretrained checkpoints, by using our visual instruction tuning data following the instructions here.

python -m llava.serve.controller --host 0.0.0.0 --port 10000

python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path ./checkpoints/LLaVA-13B-v0 --multi-modal

Wait until the process finishes loading the model and you see "Uvicorn running on ...".

If your the VRAM of your GPU is less than 24GB (e.g., RTX 3090, RTX 4090, etc.), you may try running it with multiple GPUs.

python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path ./checkpoints/LLaVA-13B-v0 --multi-modal --num-gpus 2

Wait until the process finishes loading the model and you see "Uvicorn running on ...".

python -m llava.serve.gradio_web_server --controller http://localhost:10000

A starting script for inference with LLaVA without the need of Gradio interface. The current implementation only supports for a single-turn Q-A session, and the interactive CLI is WIP. This also serves as an example for users to build customized inference scripts.

python -m llava.eval.run_llava \
    --model-name /path/to/LLaVA-13B-v0 \
    --image-file "https://llava-vl.github.io/static/images/view.jpg" \
    --query "What are the things I should be cautious about when I visit here?"

Example output (varies in different runs):

When visiting this picturesque location with a serene lake and a wooden pier extending over the water, one should be cautious about various safety aspects. Some important considerations include:

1. Ensuring that the pier is structurally sound andstable, as old or weakened pier structures might not support the weight of visitors.
2. Being aware of the water depth around the pier and lake, as sudden drop-offs or strong currents may pose a risk to swimmers, boaters, or those who venture too close to the edge.
3. Staying vigilant about the presence of wildlife in the area, such as slippery, stealthy fish or other animals that might cause harm or inconvenience.
4. Maintaining a safe distance from the water's edge, particularly for children, elderly individuals, or those who are not strong swimmers.
5. Following any posted signs or guidelines related to safety and the use of the pier and surrounding areas.

By considering these safety precautions, visitors can enjoy the natural beauty of the location while minimizing risks and ensuring a safe and pleasant experience.

Our GPT-assisted evaluation pipeline for multimodal modeling is provided for a comprehensive understanding of the capabilities of vision-language models. Please see our paper for more details.

1. Generate LLaVA responses

python model_vqa.py \
    --model-name ./checkpoints/LLaVA-13B-v0 \
    --question-file \
    playground/data/coco2014_val_qa_eval/qa90_questions.jsonl \
    --image-folder \
    /path/to/coco2014_val \
    --answers-file \
    /path/to/answer-file.jsonl

2. Evaluate the generated responses. In our case, answer-file-1.jsonl is the response generated by text-only GPT-4 (0314), with the context captions/boxes provided.

OPENAI_API_KEY="sk-***********************************" python eval_gpt_review_visual.py \
    --question playground/data/coco2014_val_qa_eval/qa90_questions.jsonl \
    --context table/caps_boxes_coco2014_val_80.jsonl \
    --answer-list \
    /path/to/answer-file-1.jsonl \
    /path/to/answer-file-2.jsonl \
    --rule table/rule.json \
    --output /path/to/review.json

3. Summarize the evaluation results

python summarize_gpt_review.py

1. Please see ScienceQA repo for setting up the dataset.
2. Generate ScienceQA dataset for LLaVA conversation-style format.

python scripts/convert_sqa_to_llava \
    convert_to_llava \
    --base-dir /path/to/ScienceQA/data/scienceqa \
    --split {train,val,minival,test,minitest}

1. Download our pretrained LLaVA-13B (delta) weights for ScienceQA dataset here. Convert the delta weights to actual weights.

python -m llava.model.apply_delta \
    --base /path/to/llama-13b \
    --target /path/to/LLaVA-13b-v0-science_qa \
    --delta liuhaotian/LLaVA-13b-delta-v0-science_qa

2. [Option 1] Multiple-GPU inference You may evaluate this with multiple GPUs, and concatenate the generated jsonl files. Please refer to our script for batch evaluation and results gathering.

3. [Option 2] Single-GPU inference

(a) Generate LLaVA responses on ScienceQA dataset

python -m llava.eval.model_vqa_science \
    --model-name /path/to/LLaVA-13b-v0-science_qa \
    --question-file /path/to/ScienceQA/data/scienceqa/llava_test.json \
    --image-folder /path/to/ScienceQA/data/scienceqa/images/test \
    --answers-file vqa/results/ScienceQA/test_llava-13b.jsonl \
    --answer-prompter
    --conv-mode simple

(b) Evaluate the generated responses

python eval_science_qa.py \
    --base-dir /path/to/ScienceQA/data/scienceqa \
    --result-file vqa/results/ScienceQA/test_llava-13b.jsonl \
    --output-file vqa/results/ScienceQA/test_llava-13b_output.json \
    --output-result vqa/results/ScienceQA/test_llava-13b_result.json \

For reference, we attach our prediction file test_llava-13b_result.json here for comparison when reproducing our results, as well as for further analysis in detail.

The current version of LLaVA is fine-tuned from a Vicuna-13B model. We use approximately 600K filtered CC3M in feature alignment pretraining and 150K GPT-generated multimodal instruction-following data in finetuning. For detailed description of the data generation pipeline, please refer see our paper.

We are working on a more capable model that is pretrained with the data at a larger scale. Stay tuned!

We release all three types of multimodal instruction-following data. The use of these data is subject to OpenAI TOS.

We fine-tune the model using the code from FastChat. We use a similar set of hyperparameters as Vicuna in finetuning. Both hyperparameters used in pretraining and finetuning are provided below.

1. Pretraining

2. Finetuning

LLaVA is trained on 8 A100 GPUs with 80GB memory with the following code. To train on fewer GPUs, you can reduce the per_device_train_batch_size and increase the gradient_accumulation_steps accordingly to keep the global batch size the same.

1. Pretraining

torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
    llava/train/train_mem.py \
    --model_name_or_path ./checkpoints/llama-vicuna-13b \
    --data_path /path/to/cc3m_595k.json \
    --image_folder /path/to/cc3m_595k \
    --vision_tower openai/clip-vit-large-patch14 \
    --tune_mm_mlp_adapter True \
    --mm_vision_select_layer -2 \
    --mm_use_im_start_end \
    --bf16 True \
    --output_dir ./checkpoints/llava-13b-pretrain \
    --num_train_epochs 1 \
    --per_device_train_batch_size 16 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 1 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 2400 \
    --save_total_limit 1 \
    --learning_rate 2e-3 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --tf32 True \
    --model_max_length 2048 \
    --gradient_checkpointing True \
    --lazy_preprocess True \
    --report_to wandb

You may run this with a single A100 GPU with the following code. Please note that the per_device_train_batch_size * gradient_accumulation_steps should be equal to 128 to keep the global batch size the same.

python llava/train/train_mem.py \
    --model_name_or_path ./checkpoints/llama-vicuna-13b \
    --data_path /path/to/cc3m_595k.json \
    --image_folder /path/to/cc3m_595k \
    --vision_tower openai/clip-vit-large-patch14 \
    --tune_mm_mlp_adapter True \
    --mm_vision_select_layer -2 \
    --mm_use_im_start_end \
    --bf16 True \
    --output_dir ./checkpoints/llava-13b-pretrain \
    --num_train_epochs 1 \
    --per_device_train_batch_size 16 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 8 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 2400 \
    --save_total_limit 1 \
    --learning_rate 2e-3 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --tf32 True \
    --model_max_length 2048 \
    --gradient_checkpointing True \
    --lazy_preprocess True \
    --report_to wandb

python llava/train/train_mem.py \
    --model_name_or_path ./checkpoints/llama-vicuna-7b \
    --data_path /path/to/cc3m_595k.json \
    --image_folder /path/to/cc3m_595k \
    --vision_tower openai/clip-vit-large-patch14 \
    --tune_mm_mlp_adapter True \
    --mm_vision_select_layer -2 \
    --mm_use_im_start_end \
    --bf16 True \
    --output_dir ./checkpoints/llava-7b-pretrain \
    --num_train_epochs 1 \
    --per_device_train_batch_size 16 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 8 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 2400 \
    --save_total_limit 1 \
    --learning_rate 2e-3 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --tf32 True \
    --model_max_length 2048 \
    --gradient_checkpointing True \
    --lazy_preprocess True \
    --report_to wandb

conda create -n llava_beta python=3.10 -y
conda activate llava_beta
pip install --upgrade pip
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu117
pip install -e .
pip install einops ninja
pip install flash-attn

torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
    llava/train/train_mem.py \
    --model_name_or_path ./checkpoints/llama-vicuna-13b \
    --data_path /path/to/cc3m_595k.json \
    --image_folder /path/to/cc3m_595k \
    --vision_tower openai/clip-vit-large-patch14 \
    --tune_mm_mlp_adapter True \
    --mm_vision_select_layer -2 \
    --mm_use_im_start_end \
    --bf16 True \
    --output_dir ./checkpoints/llava-13b-pretrain_fsdp \
    --num_train_epochs 1 \
    --per_device_train_batch_size 16 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 1 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 2400 \
    --save_total_limit 1 \
    --learning_rate 2e-3 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --tf32 True \
    --fsdp "full_shard auto_wrap" \
    --fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
    --model_max_length 2048 \
    --gradient_checkpointing True \
    --lazy_preprocess True \
    --report_to wandb

2. Extract projector features

python scripts/extract_mm_projector.py \
  --model_name_or_path ./checkpoints/llava-13b-pretrain \
  --output ./checkpoints/mm_projector/llava-13b-pretrain.bin

3. Finetuning

torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
    llava/train/train_mem.py \
    --model_name_or_path /path/to/llama-vicuna-13b \
    --data_path /path/to/llava_instruct_150k.json \
    --image_folder /Data/haotian/coco/train2014 \
    --vision_tower openai/clip-vit-large-patch14 \
    --pretrain_mm_mlp_adapter ./checkpoints/mm_projector/llava-13b-pretrain.bin \
    --mm_vision_select_layer -2 \
    --mm_use_im_start_end True \
    --bf16 True \
    --output_dir ./checkpoints \
    --num_train_epochs 3 \
    --per_device_train_batch_size 4 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 1 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 5000 \
    --save_total_limit 3 \
    --learning_rate 2e-5 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --tf32 True \
    --fsdp "full_shard auto_wrap" \
    --fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
    --model_max_length 2048 \
    --gradient_checkpointing True \
    --lazy_preprocess True \
    --report_to wandb

LLaVA-Lightning can be trained on 8x A100 GPUs in just 3 hours, including both pretraining and finetuning. When using spot instances, it costs just ~$40. We are working on SkyPilot tutorial to make spot instance training even easier, stay tuned!

Please make sure to: (1) install or upgrade to the latest code base, and (2) pass the correct model version identifier v0/v1 to ensure the correct conversation template is loaded.

bash ./scripts/train_lightning.sh {v0,v1}

1. Pretraining

2. Finetuning

Thanks to LLaVA-Lightning, we are able to train a checkpoint based on MPT-7b-Chat on 8x A100 GPUs in just 3 hours, including both pretraining and finetuning.

NOTE: This is a research preview of the LLaVA-Lightning based on MPT-7B-chat checkpoint. The usage of the model should comply with MPT-7B-chat license and agreements.

NOTE: Unlike other LLaVA models, this model should be used directly without delta weights conversion!

NOTE: You need to upgrade to our latest code base to use LLaVA-MPT-7b!

1. Usage

You do not need to download our checkpoint, it will directly load from our Hugging Face model: liuhaotian/LLaVA-Lightning-MPT-7B-preview.

python -m llava.serve.controller --host 0.0.0.0 --port 10000
python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path liuhaotian/LLaVA-Lightning-MPT-7B-preview
python -m llava.serve.gradio_web_server --controller http://localhost:10000

2. Training

We use the same set of training dataset, and the hyperparameters as other Lightning checkpoints.

bash ./scripts/train_lightning_mpt.sh

NOTE: Due to that ScienceQA experiments were done earlier, the current checkpoints are trained without <im_start> and <im_end> tokens. Checkpoints with these tokens will be updated later. Here we provide our training scripts for the current checkpoints.

torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
    llava/train/train_mem.py \
    --model_name_or_path ./checkpoints/llama-vicuna-13b \
    --data_path /path/to/cc3m_595k.json \
    --image_folder /path/to/cc3m_595k \
    --vision_tower openai/clip-vit-large-patch14 \
    --tune_mm_mlp_adapter True \
    --mm_vision_select_layer -2 \
    --bf16 True \
    --output_dir ./checkpoints/llava-13b-pretrain-no_im_start_end_token \
    --num_train_epochs 1 \
    --per_device_train_batch_size 16 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 1 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 2400 \
    --save_total_limit 1 \
    --learning_rate 2e-3 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --tf32 True \
    --model_max_length 2048 \
    --gradient_checkpointing True \
    --lazy_preprocess True \
    --report_to wandb

python scripts/extract_mm_projector.py \
  --model_name_or_path ./checkpoints/llava-13b-pretrain-no_im_start_end_token \
  --output ./checkpoints/mm_projector/llava-13b-pretrain-no_im_start_end_token.bin

torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
    llava/train/train_mem.py \
    --model_name_or_path /path/to/llama-vicuna-13b \
    --data_path /path/to/scienceqa/llava_train_QCM-LEPA.json \
    --image_folder /path/to/scienceqa/images/train \
    --vision_tower openai/clip-vit-large-patch14 \
    --pretrain_mm_mlp_adapter ./checkpoints/mm_projector/llava-13b-pretrain-no_im_start_end_token.bin \
    --mm_vision_select_layer -2 \
    --bf16 True \
    --output_dir ./checkpoints/llava-13b-pretrain-no_im_start_end_token-finetune_scienceqa \
    --num_train_epochs 12 \
    --per_device_train_batch_size 4 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 1 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 5000 \
    --save_total_limit 3 \
    --learning_rate 2e-5 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --tf32 True \
    --fsdp "full_shard auto_wrap" \
    --fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
    --model_max_length 2048 \
    --gradient_checkpointing True \
    --lazy_preprocess True \
    --report_to wandb

• Vicuna: the codebase we built upon, and our base model Vicuna-13B that has the amazing language capabilities!

If you find LLaVA useful for your your research and applications, please cite using this BibTeX:

@misc{liu2023llava,
      title={Visual Instruction Tuning}, 
      author={Liu, Haotian and Li, Chunyuan and Wu, Qingyang and Lee, Yong Jae},
      publisher={arXiv:2304.08485},
      year={2023},
}

• Instruction Tuning with GPT-4

For future project ideas, pleae check out:

• SEEM: Segment Everything Everywhere All at Once
• Grounded-Segment-Anything to detect, segment, and generate anything by marrying Grounding DINO and Segment-Anything.