Fine tuning is moderately intense. Going from base LLaMA to Vicuna 13B costs abo... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

valine on May 23, 2023 | parent | context | favorite | on: Bringing the power of AI to Windows 11

Fine tuning is moderately intense. Going from base LLaMA to Vicuna 13B costs about $300.

brucethemoose2 on May 23, 2023 [–]

The compute requirements are reasonable, but the memory requirements are extremely high, even with some upcoming breakthroughs like 4 bit bitsandbytes.

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