is the finetuning more like "instruct-finetuning" ? I would like to try it out for a sample usecase I have but to proceed it would be better to know the fundamentals behind it
Show HN: Toolkit for LLM Fine-Tuning, Ablating and Testing
21–22 of 22 posts
Re: Show HN: Toolkit for LLM Fine-Tuning, Ablating and Testing
#22This 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?