Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
Simple GRPO – RL for 8B models on $10/h GPUs
github.com/minosvasilias
1 point
minosu
a year ago
Loading...
Simple GRPO – RL for 8B models on $10/h GPUs | Heykuki News