ariveinberg-max/aven-1

A from-scratch causal Transformer trained from random weights, no pretrained model or API.

2 best points · 0 comments · 1 Hacker News post · 1 GitHub stars · View on GitHub

Hacker News discussions

• I built a 20M-parameter LLM from scratch, including full RLHF (PPO) (2 points, 0 comments, by neurovance, 2026-09-08)