Replies: 4 comments 12 replies
-
当前Prompt的使用流程: |
Beta Was this translation helpful? Give feedback.
-
另外一个模型输入适配, 需要dbgpt-server和llm-server交互是结构化的,而非文本化的。 |
Beta Was this translation helpful? Give feedback.
-
多模型的支持和部署还是挺复杂的:不同的prompt、多卡的支持,这里的工作很多fastchat已经做了,我们是不是可以考虑直接对接它,当然简单的私有化部署也很重要,它里面也有一些我们不需要的功能。 |
Beta Was this translation helpful? Give feedback.
-
@yhjun1026 如上,目前主要两个点:
如果没别的问题的话我可以开发这两个功能,分两个pr提。 |
Beta Was this translation helpful? Give feedback.
-
Different LLM models have different requirements for input structure and support for prompts and examples. We hope to optimize the overall design so that different models can perform better
Beta Was this translation helpful? Give feedback.
All reactions