Pushing the capabilities of Gemma 3 via distillation and RL fine-tuning

Estimated read time 1 min read

Post Content

​ Specialized capabilities (e.g. math abilities, coding, multilinguality, tool use…) are key areas of improvement in post-training. In this talk we explore a novel strategy involving large-scale distillation and RL finetuning to push specialized capabilities in LMs while still improving their generality.

Subscribe to Google for Developers → https://goo.gle/developers

Speakers: Johan Ferret
Products Mentioned: Gemma   Read More Google for Developers 

You May Also Like

More From Author