title: README
emoji: 👁
colorFrom: yellow
colorTo: blue
sdk: static
pinned: false
2021年11月22日, IDEA 研究院创院理事长沈向阳在IDEA大会上正式宣布启动“封神榜”大模型开源体系。“封神榜”是由 IDEA-CCNL 的工程师、研究人员、实习生团队共同维护的一项长期开源计划。项目基于Apache 2.0开源许可,计划包括封神榜模型,封神框架还有封神榜单三个部分。封神榜的模型可以在 HuggingFace 社区中免费下载和使用,封神框架可以通过访问我们的GitHub获得: Fengshenbang-LM 。封神榜单将会在未来数月内完善并正式公布。
“封神榜”开源体系将会重新审视整个中文预训练大模型开源社区,全方位的推进整个中文大模型社区的发展,旨在成为中文认知智能的基础设施。
IDEA (International Digital Economy Academy) officially announces the launch of "Fengshenbang" open source project. "Fengshenbang" is an ongoing effort maintained by the team of engineers, researches and interns at IDEA-CCNL. Based on the Apache 2.0 license, this project includes three parts: Fengshenbang Model, Fengshen Framework and Fengshen Benchmark. Fengshenbang Model canb e downloaded and used for free in the HuggingFace community, the Fengshen Framework can be obtained by visiting our GitHub: Fengshenbang-LM. Fengshen Benchmark will be improved and officially announced in the next few months.
"Fengshenbang" will re-examine the entire Chinese pre-trained model open-source community, promote the development of the entire Chinese large-scale model community. We aspire to be the Foundation of Chinese Cognitive Intelligence.