csg-wukong-1B [中文] [English]
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 Description
csg-wukong-1B is a 1 billion-parameter small language model(SLM) pretrained on 1T tokens. we will introduce more information about csg-wukong-1B.
Model Evaluation results
We submitted csg-wukong-1B on the open_llm_leaderboard, and the results show our model ranked the 8th among the ~1.5B pretrained small language models.

Training
Hardware
- GPUs: 16 H800
- Training time: 43days
Software
OpenCSG介绍
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。
模型介绍
csg-wukong-1B 是一个1B参数量的小语言模型,该模型训练了1T tokens.
我们将在后面介绍更多关于这个模型的信息。
模型评测结果
我们把csg-wukong-1B模型提交到open_llm_leaderboard榜单上,结果显示我们的模型目前在~1.5B小语言模型中排名第8。

训练
硬件资源
- GPU数量: 16 H800
- 训练时间: 43天