I built a 20M-parameter LLM from scratch, including full RLHF (PPO)
By neurovance · 2026-09-08 · 2 points · 0 comments
https://github.com/ariveinberg-max/aven-1
By neurovance · 2 points · 0 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews