Skip to content

Conversation

@thirdgerb
Copy link
Contributor

support deepseek-r1.

  • support deepseek-r1
    • consider deepseek api protocol is different from openai, add deepseek api adapter.
    • implement message stage.
    • thread history message to prompt filter by stages [""] as default.
  • streamlit chat with ghost support staging message stream.
  • openai o1 do not support system/developer message now, add new compatible option to the model.
  • now llm model and service both have attribute compatible to set universe compatible options.
  • prompt object add first_token attribute for debugging.
  • fix bugs
    • fix shell does not close conversation correctly
    • fix sequence pipeline handle multiple complete message wrong.

@thirdgerb thirdgerb merged commit 09687de into main Jan 22, 2025
@thirdgerb thirdgerb deleted the feat/deepseek-reasoning branch January 22, 2025 08:12
@Misakar-0v0
Copy link
Contributor

Misakar-0v0 commented Jan 22, 2025

  • openai o1 do not support system/developer message now, add new compatible option to the model.

这里openai o1 应该是 deepseek r1?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants