Dark Hacker News
new
|
best
|
ask
|
show
|
jobs
popopanda | Dark Hacker News
user:
popopanda
created:
December 27, 2025
karma:
7
submissions
comments
1.
Show HN: Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)
(github.com)
9 points
by
popopanda
6 hours ago
|
0 comments