ttumiel / minRLHFLinks
Minimal RLHF implementation built on top of minGPT.
☆30Updated last year
Alternatives and similar repositories for minRLHF
Users that are interested in minRLHF are comparing it to the libraries listed below
Sorting:
- Implementation of ICLR 2025 paper "Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation"☆18Updated last year
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆32Updated last year
- Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)☆42Updated last year
- NeurIPS 2024 tutorial on LLM Inference☆47Updated last year
- Dateset Reset Policy Optimization☆31Updated last year
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆28Updated 2 years ago
- ☆160Updated last year
- Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models☆68Updated 8 months ago
- Offline RL experiments☆15Updated 3 years ago
- Verlog: A Multi-turn RL framework for LLM agents☆67Updated last week
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆70Updated 9 months ago
- Natural Language Reinforcement Learning☆101Updated 5 months ago
- Representation Learning in RL☆13Updated 3 years ago
- Bayes-Adaptive RL for LLM Reasoning☆43Updated 7 months ago
- Code for the paper: Dense Reward for Free in Reinforcement Learning from Human Feedback (ICML 2024) by Alex J. Chan, Hao Sun, Samuel Holt…☆38Updated last year
- ☆107Updated last year
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆26Updated 2 months ago
- ☆57Updated last year
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆47Updated last year
- Reinforcement Learning via Regressing Relative Rewards☆38Updated last year
- Code for Contrastive Preference Learning (CPL)☆177Updated last year
- ☆51Updated last year
- ☆33Updated last year
- AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning (Published in TMLR)☆22Updated last year
- ☆35Updated 10 months ago
- ☆109Updated last year
- Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients☆26Updated last year
- Implementation of ICML 2023 paper: Future-conditioned Unsupervised Pretraining for Decision Transformer☆29Updated 2 years ago
- Fast reinforcement learning 💨☆28Updated 5 months ago
- The official code release for Q#: Provably Optimal Distributional RL for LLM Post-Training☆17Updated 10 months ago