lucidrains/self-rewarding-lm-pytorch

Post-training with Tinker

AllenAI's post-training codebase

PyTorch native post-training library

Train transformer language models with reinforcement learning.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Stanford NLP Python library for Representation Finetuning (ReFT)

A Lightweight LLM Post-Training Library

Training Sparse Autoencoders on Language Models

Scalable toolkit for efficient model reinforcement