Hacker News new | past | comments | ask | show | jobs | submit login
2x faster Gemma 2 finetuning and 63% less VRAM (unsloth.ai)
3 points by ricopags 6 months ago | hide | past | favorite | 1 comment



Gemma 2 27B is currently the best performing 'open' model [license is non-commercial].

The Unsloth team have a blog post up where they've made fine-tuning Gemma 2 require less VRAM, and also have extended the context window.

They've also updated their 'mistralified' PHI-3 models to Microsoft's June update of PHI-3 which sees some performance increases as well.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: