---
license: apache-2.0
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct-Instruct
---
# **OpenCSG-Qwen2.5-3B-GUI**          [[中文]](#chinese)    [[English]](#english)

<a id="english"></a>

<p align="center">
<img width="300px" alt="OpenCSG" src="https://cdn-uploads.huggingface.co/production/uploads/64c71b27d43e4dee51a8b31a/GwYXPKuEoGCGcMICeW-sb.jpeg">
</p>

<p align="center"><a href="https://portal.opencsg.com/models">[OpenCSG Community]</a>   <a href="https://github.com/opencsgs">[github]</a>  <a href="https://cdn-uploads.huggingface.co/production/uploads/64c71b27d43e4dee51a8b31a/HU6vz21qKTEmUBCWqCFh9.jpeg">[wechat]</a>  <a href="https://twitter.com/OpenCsg">[Twitter]</a> </p>


</div>
OpenCSG stands for Converged resources, Software refinement, and Generative LM. The 'C' represents Converged resources, indicating the integration and full utilization of hybrid resources. The 'S' stands for Software refinement, signifying software that is refined by large models. The 'G' represents Generative LM, which denotes widespread, inclusive, and democratized generative large models.

The vision of OpenCSG is to empower every industry, every company, and every individual to own their models. We adhere to the principles of openness and open source, making the large model software stack of OpenCSG available to the community. We welcome everyone to use, send feedback, and contribute collaboratively.





# Model 

*OpenCSG-Qwen2.5-3B-GUI* is an automation assistant model optimized based on large language models (LLM) developed by the OpenCSG team. It provides a powerful intelligent dialogue system and automation capabilities for the [AutoHub](https://opencsg.com/autohub) browser plugin, allowing users to interact with their browsers using natural language. This model is specifically designed to enhance the user’s web browsing automation experience, efficiently handling tasks such as web operations, information retrieval, and task automation.


# Training

## Hardware

- **GPUs:** 8 Tesla A800 
- **Training time:** 7 hours

## Software

- **Orchestration:** [Deepspeed](https://github.com/OpenCSGs)
- **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch)
- **BP16 if applicable:** [apex](https://github.com/NVIDIA/apex)


<a id="chinese"></a>

<p>

</p>

# OpenCSG介绍


<p align="center">
<img width="300px" alt="OpenCSG" src="https://cdn-uploads.huggingface.co/production/uploads/64c71b27d43e4dee51a8b31a/GwYXPKuEoGCGcMICeW-sb.jpeg">
</p>

<p align="center"><a href="https://opencsg.com/models">[OpenCSG 社区]</a>   <a href="https://github.com/opencsgs">[github]</a>  <a href="https://cdn-uploads.huggingface.co/production/uploads/64c71b27d43e4dee51a8b31a/HU6vz21qKTEmUBCWqCFh9.jpeg">[微信]</a>  <a href="https://twitter.com/OpenCsg">[推特]</a> </p>



</div>
OpenCSG中 Open是开源开放；C 代表 Converged resources，整合和充分利用的混合异构资源优势，算力降本增效；S 代表 Software refined，重新定义软件的交付方式，通过大模型驱动软件开发，人力降本增效；G 代表 Generative LM，大众化、普惠化和民主化的可商用的开源生成式大模型。

OpenCSG的愿景是让每个行业、每个公司、每个人都拥有自己的模型。 我们坚持开源开放的原则，将OpenCSG的大模型软件栈开源到社区，欢迎使用、反馈和参与共建，欢迎关注。



# 模型简介

*OpenCSG-Qwen2.5-3B-GUI* 是一个由 OpenCSG 团队开发的基于大型语言模型（LLM）优化的自动化助手模型。它为 [AutoHub](https://opencsg.com/autohub) 插件提供了强大的智能对话系统和自动化功能，支持用户通过自然语言与浏览器进行交互。该模型专为提升用户的网页浏览自动化体验而设计，能够高效地处理网页操作、信息检索、任务自动化等工作。

## 硬件资源

- **GPU数量：** 8 Tesla A800 
- **训练时间：** 12 小时

## 软件使用

- **微调训练框架：** [Deepspeed](https://github.com/OpenCSGs)
- **深度学习框架：** [PyTorch](https://github.com/pytorch/pytorch)
- **BP16：** [apex](https://github.com/NVIDIA/apex)