---
license: apache-2.0
metrics:
- accuracy
base_model:
- liuhaotian/llava-v1.5-7b
---
# LLaVA-3D

##  Table of Contents

1. [Model Summary](##model-summary)
2. [Use](##use)
3. [Limitations](##limitations)
4. [Training](##training)
5. [License](##license)
6. [Citation](##citation)

## Model Summary

The LLaVA-3D model is a 7B parameter models trained on LLaVA-3D-Instruct-1M, based on LLaVA-v1.5-7B.

- **Repository:** [ZCMax/LLaVA-3D](https://github.com/ZCMax/LLaVA-3D)
- **Project Website:** [zcmax.github.io/projects/LLaVA-3D](https://zcmax.github.io/projects/LLaVA-3D/)
- **Paper:** [LLaVA-3D](https://arxiv.org/abs/2409.18125)
- **Point of Contact:** [Chenming Zhu](mailto:zcm952742165@gmail.com)
- **Languages:** English


## Use

### Intended use

The model was trained on LLaVA-3D-Instruct-1M and has the ability to interact with the single image for 2D tasks and posed RBG-D images for 3D tasks. 

**Feel free to share your generations in the Community tab!**

# Training

## Model

- **Pretraining Stage:** scene-level and region-level caption data, 1 epoch, projector
- **Instructing Tuning Stage:** A mixture of 1M high-quality 2D and 3D data, 1 epoch, full model
- **Precision:** bfloat16

## Hardware & Software

- **GPUs:** 8 * Nvidia Tesla A100 (for whole model series training)
- **Orchestration:** [Huggingface Trainer](https://huggingface.co/docs/transformers/main_classes/trainer)
- **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch)

# Citation
```
@article{zhu2024llava,
  title={LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness},
  author={Zhu, Chenming and Wang, Tai and Zhang, Wenwei and Pang, Jiangmiao and Liu, Xihui},
  journal={arXiv preprint arXiv:2409.18125},
  year={2024}
}
```