This topic created in 1161 days ago, the information mentioned may be changed or developed.
 |
1
crokily Feb 23, 2023  1
3 周前传上 github 的项目
7 天前开始发了几篇公关稿，话术是“超越 GPT3.5” 现在好像没啥热度，没搜到相关的讨论 不知道表现咋样 |
 |
2
eason1874 Feb 23, 2023
吊打？真的吗？我不信
|
|
3
crokily Feb 23, 2023
|
 |
5
lovestudykid Feb 24, 2023
>fine-tuning a smaller model with task-specific datasets (rather than feeding in-context learning demos to a larger generalist LLM) is exactly what we wanted in this study
一句话总结，不要拿去跟 chatgpt 比 |
Select Language