OpenBMB / MiniCPM

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.
Apache License 2.0
4.67k stars 334 forks source link

[Feature Request]: 训练策略 #38

Closed xxw1995 closed 6 months ago

xxw1995 commented 6 months ago

Feature request / 功能建议

训练策略相关代码有计划开源吗?

ShengdingHu commented 6 months ago

抱歉,我们可能不会开源训练策略相关的代码,因为其中有比较多内部研发用的框架的内容。训练策略已公开在https://shengdinghu.notion.site/MiniCPM-c805a17c5c8046398914e47f0542095a,感谢关注! Sorry, we may not open source the code related to training strategies, as it contains a lot of content from our internal research and development frameworks. The training strategies have been published at https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20. Thank you for your interest!