alt
Hacker News
Show HN: Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)
13 points
•
by
popopanda
•
today at 12:30 PM
•
0 comments
•
view on HN
Comments
popopanda
•
today at 12:31 PM
[flagged]
alt Hacker News
[flagged]