Live data from Hacker News

Show HN: Toolkit for LLM Fine-Tuning, Ablating and Testing

github.com

21–22 of 22 posts

Re: Show HN: Toolkit for LLM Fine-Tuning, Ablating and Testing

#22
This tool looks super interesting! I had a question- You mentioned the ability to run tests to ensure the fine-tuned model behaves as expected. What evaluation metrics are built in, and how customizable is the evaluation pipeline? Can I easily add my own metrics?
Post reply on HN