pull down to refresh

Train your own R1 reasoning model locallyunsloth.ai/blog/r1-reasoning
214 sats \ 1 comment \ @aljaz 7 Feb 2025 AI
write
preview
related posts
20 sats \ 0 replies \ @zuspotirko 7 Feb 2025
Please note, this isn’t fine-tuning

> look inside

> it's fine tuning

reply