NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
▲Show HN: Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO) (github.com)
20 points by popopanda 19 hours ago | 0 comments
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 07:10:05 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.