most citedZephyr: Direct Distillation of LM Alignment

56 citations · 61 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG20242 cited

The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization

Shengyi Huang, Michael Noukhovitch, Arian Hosseini +3

This work is the first to openly reproduce the Reinforcement Learning from Human Feedback (RLHF) scaling behaviors reported in OpenAI's seminal TL;DR summarization work. We create…

cs.LG20243 cited

Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

Shengyi Huang, Quentin Gallouédec, Florian Felten +30

In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curv…

cs.LG2023

Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks

Ryan Sullivan, Akarsh Kumar, Shengyi Huang +2

Most reinforcement learning methods rely heavily on dense, well-normalized environment rewards. DreamerV3 recently introduced a model-based method with a number of tricks that miti…

cs.LG202356 cited

Zephyr: Direct Distillation of LM Alignment

Lewis Tunstall, Edward Beeching, Nathan Lambert +11

We aim to produce a smaller language model that is aligned to user intent. Previous research has shown that applying distilled supervised fine-tuning (dSFT) on larger models signif…

cs.LG2023

Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform

Shengyi Huang, Jiayi Weng, Rujikorn Charakorn +3

Distributed Deep Reinforcement Learning (DRL) aims to leverage more computational resources to train autonomous agents with less training time. Despite recent progress in the field…