https://github.com/foundationvision/groma
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
https://github.com/foundationvision/groma
foundation-models grounding large-language-models llama llama2 llm mllm multimodal vision-language-model
Last synced: 6 months ago
JSON representation
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
- Host: GitHub
- URL: https://github.com/foundationvision/groma
- Owner: FoundationVision
- License: apache-2.0
- Created: 2024-04-21T08:08:59.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-06-07T06:51:14.000Z (over 1 year ago)
- Last Synced: 2024-10-29T17:12:20.623Z (11 months ago)
- Topics: foundation-models, grounding, large-language-models, llama, llama2, llm, mllm, multimodal, vision-language-model
- Language: Python
- Homepage: https://groma-mllm.github.io/
- Size: 13.5 MB
- Stars: 553
- Watchers: 35
- Forks: 58
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Groma: Grounded Multimodal Assistant
> [**Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models**](https://arxiv.org/abs/2404.13013)
> **Chuofan Ma, Yi Jiang, Jiannan Wu, Zehuan Yuan, Xiaojuan Qi**
>
>
>
>
>
Groma is an MLLM with exceptional region understanding and visual grounding capabilities. It can take user-defined region inputs (boxes) as well as generate long-form responses that are grounded to visual context.
Groma presents a novel paradigm of grounded MLLMs. (a) LLM for localization (e.g., Kosmos-2, Shikra); (b) External modules for localization (e.g., Lisa); and (c) Visual tokenier for localization (Groma).
## Contents
- [Install](#installation)
- [Model](#model-weights)
- [Data](#prepare-data)
- [Training](#training)
- [Inference](#inference)
- [Evaluation](#evaluation)
## Performance
State-of-the-art performance on referring expression comprehension (REC) benchmarks among multimodal
large language models.
Method
RefCOCO
RefCOCO+
RefCOCOg
Avergae
val
testA
testB
val
testA
testB
val
test
Shikra
87.01
90.61
80.24
81.60
87.36
72.12
82.27
82.19
82.93
Ferret
87.49
91.35
82.45
80.78
87.38
73.14
83.93
84.76
83.91
MiniGPT-v2
88.69
91.65
85.33
79.97
85.12
74.45
84.44
84.66
84.29
Qwen-VL
89.36
92.26
85.34
83.12
88.25
77.21
85.58
85.48
85.83
Groma
89.53
92.09
86.26
83.90
88.91
78.05
86.37
87.01
86.52
## Installation
Clone the repository
~~~
git clone https://github.com/FoundationVision/Groma.git
cd Groma
~~~
Create the conda environment and install dependencies
~~~
conda create -n groma python=3.9 -y
conda activate groma
conda install pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=11.8 -c pytorch -c nvidia
pip install --upgrade pip # enable PEP 660 support
pip install -e .
cd mmcv
MMCV_WITH_OPS=1 pip install -e .
cd ..
~~~
Install falsh-attention for training
~~~
pip install ninja
pip install flash-attn --no-build-isolation
~~~
## Model Weights
To play with Groma, please download the [model weights](https://huggingface.co/FoundationVision/groma-7b-finetune) from huggingface.
We additionally provide pretrained checkpoints from intermediate training stages.
You can start from any point to customize training.
| Training stage | Required checkpoints |
|:--------------:|:--------------------:|
| Detection pretraining | [DINOv2-L](https://huggingface.co/facebook/dinov2-large) |
| Alignment pretraining | [Vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5), [Groma-det-pretrain](https://huggingface.co/FoundationVision/groma-det-pretrain) |
| Instruction finetuning | [Groma-7b-pretrain](https://huggingface.co/FoundationVision/groma-7b-pretrain) |
## Prepare Data
We provide instructions to download datasets used at different training stages of Groma,
including [Groma Instruct](https://huggingface.co/datasets/FoundationVision/groma_instruct/),
a 30k viusally grounded conversation dataset constructed with GPT-4V.
You don't have to download all of them unless you want to train Groma from scratch.
Please follow instructions in [DATA.md](docs/DATA.md) to prepare datasets.
Training stage
Data types
Datasets
Detection pretraining
Detection
COCO, Objects365, OpenImages, V3Det, SA1B
Alignment pretraining
Image caption
ShareGPT-4V-PT
Grounded caption
Flickr30k Entities
Region caption
Visual Genome, RefCOCOg
REC
COCO, RefCOCO/g/+, Grit-20m
Instruction finetuning
Grounded caption
Flickr30k Entities
Region caption
Visual Genome, RefCOCOg
REC
COCO, RefCOCO/g/+
Instruction following
Groma Instruct, LLaVA Instruct, ShareGPT-4V
## Training
For detection pretraining, please run
~~~
bash scripts/det_pretrain.sh {path_to_dinov2_ckpt} {output_dir}
~~~
For alignment pretraining, please run
~~~
bash scripts/vl_pretrain.sh {path_to_vicuna_ckpt} {path_to_groma_det_pretrain_ckpt} {output_dir}
~~~
For instruction finetuning, please run
~~~
bash scripts/vl_finetune.sh {path_to_groma_7b_pretrain_ckpt} {output_dir}
~~~
## Inference
To test on single image, you can run
~~~
python -m groma.eval.run_groma \
--model-name {path_to_groma_7b_finetune} \
--image-file {path_to_img} \
--query {user_query} \
--quant_type 'none' # support ['none', 'fp16', '8bit', '4bit'] for inference
~~~
## Evaluation
For evaluation, please refer to [EVAL.md](docs/EVAL.md) for more details.
## Citation
If you find this repo useful for your research, feel free to give us a star ⭐ or cite our paper:
```
@article{ma2024groma,
title={Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models},
author={Ma, Chuofan and Jiang, Yi and Wu, Jiannan and Yuan, Zehuan and Qi, Xiaojuan},
journal={arXiv preprint arXiv:2404.13013},
year={2024}
}
```
## Acknowledgement
Groma is built upon the awesome works
[LLaVA](https://github.com/haotian-liu/LLaVA/) and
[GPT4ROI](https://github.com/jshilong/GPT4RoI).
## LICENSE
This project is licensed under the Apache License 2.0 -
see the [LICENSE](LICENSE) file for details.