Griffith-7/Tpo-torch

A clean, production-ready PyTorch implementation of Target Policy Optimization (TPO) for stable RLHF alignment.

1 best points · 1 comments · 1 Hacker News post · 4 GitHub stars · View on GitHub

Hacker News discussions

• Tpo-Torch – Target Policy Optimization for Stable RLHF Alignment in PyTorch (1 points, 1 comments, by Griffith-7, 2026-07-21)