News for hackers. Stuff that matters.

A comment on Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models. Parent comment

Re:Fine-Tuning Llama-2: A Comprehensive Case Study for Tailo... by mikeravkine on Friday August 11, 2023 @03:55PM (#37093234)
The model card also has prompt formats for context aware document Q/A and multi-CoT, using those correctly improves performance at such tasks significantly.
[ Parent | on HN ]

There are no comments on this comment yet.