News for hackers. Stuff that matters.

A comment on Gemma 3 270M: The compact model for hyper-efficient AI. Parent comment

Re:Gemma 3 270M: The compact model for hyper-efficient AI by JLCarveth on Thursday August 14, 2025 @06:07PM (#44906258)
I ran into the same looping issue with that model.
[ Parent | on HN ]
Re:Gemma 3 270M: The compact model for hyper-efficient AI by danielhanchen on Thursday August 14, 2025 @07:53PM (#44907098)
Definitely give

temperature = 1.0, top_k = 64, top_p = 0.95, min_p = 0.0

a try, and maybe repeat_penalty = 1.1

[ Parent | on HN ]