p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
Paper
•
2412.04449
•
Published
•
7
This is the official model checkpoint of p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay. Please refer to this repository for our code.
This model is pretrained on LCS-558K image caption data, and instruction-tuned on llava-v1_5-mix-665k.
If you find our work helpful for your research and applications, please cite our paper:
@article{zhang2024pmod,
title={p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay},
author={Zhang, Jun and Meng, Desen and Qi, Ji and Huang, Zhenpeng and Wu, Tao and Wang, Limin},
journal={arXiv preprint arXiv:2412.04449},
year={2024}
}
Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
Base model
lmsys/vicuna-7b-v1.5