from Hacker News

Reflection-Tuning allows LLMs to detect mistakes in reasoning and self-correct

by sweca on 9/6/24, 5:31 PM with 1 comments

• by sweca on 9/6/24, 5:32 PM

  Ollama has added support in a prerelease version.

  https://github.com/ollama/ollama/releases/tag/v0.3.10-rc1