---
base_model: Qwen/Qwen2.5-3B-Instruct
library_name: peft
license: mit
datasets:
- RussianNLP/Mixed-Summarization-Dataset
language:
- ru
pipeline_tag: summarization
---

# InternVL2_5-4B-QLoRA-LLM-RussianSummarization

[\[📂 GitHub\]](https://github.com/H1merka/InternVL2_5-4B-QLoRA-LLM-RussianSummarization)  [\[🤗 HF\]](https://huggingface.co/H1merka/InternVL2_5-4B-QLoRA-LLM-RussianSummarization)

## Introduction

This is the QLoRA adapter for LLM part of [InternVL2_5-4B](https://huggingface.co/OpenGVLab/InternVL2_5-4B) multimodal model

## Model architecture

For more information you can visit these pages:

Full model: [InternVL2_5-4B](https://huggingface.co/OpenGVLab/InternVL2_5-4B)

LLM part: [Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)

ViT: [InternViT-300M-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-300M-448px-V2_5)

## Fine-tuning strategy

Fine-tuning was made using QLoRA method on Kaggle GPU P100 with 10000 elements from [Mixed-Summarization-Dataset](https://huggingface.co/datasets/RussianNLP/Mixed-Summarization-Dataset) dataset

## Results

Training loss, validation loss, SummaC were chosen as evaluation metrics.

![image/png](https://raw.githubusercontent.com/H1merka/InternVL2_5-4B-QLoRA-LLM-RussianSummarization/main/Charts.png)

## License

This project is released under the MIT License. This project uses the pre-trained Qwen2.5-3B-Instruct, which is licensed under the Apache License 2.0.

## Citation

If you find this project useful in your research, please consider citing:

```BibTeX
@article{chen2024expanding,
  title={Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling},
  author={Chen, Zhe and Wang, Weiyun and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Cui, Erfei and Zhu, Jinguo and Ye, Shenglong and Tian, Hao and Liu, Zhaoyang and others},
  journal={arXiv preprint arXiv:2412.05271},
  year={2024}
}
@article{gao2024mini,
  title={Mini-internvl: A flexible-transfer pocket multimodal model with 5\% parameters and 90\% performance},
  author={Gao, Zhangwei and Chen, Zhe and Cui, Erfei and Ren, Yiming and Wang, Weiyun and Zhu, Jinguo and Tian, Hao and Ye, Shenglong and He, Junjun and Zhu, Xizhou and others},
  journal={arXiv preprint arXiv:2410.16261},
  year={2024}
}
@article{chen2024far,
  title={How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites},
  author={Chen, Zhe and Wang, Weiyun and Tian, Hao and Ye, Shenglong and Gao, Zhangwei and Cui, Erfei and Tong, Wenwen and Hu, Kongzhi and Luo, Jiapeng and Ma, Zheng and others},
  journal={arXiv preprint arXiv:2404.16821},
  year={2024}
}
@inproceedings{chen2024internvl,
  title={Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks},
  author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={24185--24198},
  year={2024}
}
```