hkproj / rlhf-ppoLinks
Notes and commented code for RLHF (PPO)
☆97Updated last year
Alternatives and similar repositories for rlhf-ppo
Users that are interested in rlhf-ppo are comparing it to the libraries listed below
Sorting:
- nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)☆108Updated 2 months ago
- Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"☆244Updated 2 months ago
- Minimal hackable GRPO implementation☆252Updated 5 months ago
- Direct Preference Optimization from scratch in PyTorch☆101Updated 3 months ago
- A project to improve skills of large language models☆456Updated this week
- ☆142Updated 2 months ago
- ☆88Updated 9 months ago
- ☆303Updated last month
- ☆127Updated last year
- Advanced NLP, Spring 2025 https://cmu-l3.github.io/anlp-spring2025/☆58Updated 3 months ago
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆195Updated last week
- [ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning☆357Updated 10 months ago
- [NeurIPS 2024] Agent Planning with World Knowledge Model☆141Updated 6 months ago
- LLaMA 2 implemented from scratch in PyTorch☆337Updated last year
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆98Updated 4 months ago
- A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.☆112Updated 5 months ago
- minimal GRPO implementation from scratch☆92Updated 4 months ago
- ☆585Updated 3 months ago
- AN O1 REPLICATION FOR CODING☆335Updated 7 months ago
- Code for the paper: "Learning to Reason without External Rewards"☆319Updated this week
- ☆238Updated last month
- A curated collection of LLM reasoning and planning resources, including key papers, limitations, benchmarks, and additional learning mate…☆281Updated 4 months ago
- Code for STaR: Bootstrapping Reasoning With Reasoning (NeurIPS 2022)☆206Updated 2 years ago
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆268Updated 4 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆226Updated 2 months ago
- ☆144Updated 7 months ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆223Updated 2 months ago
- Tina: Tiny Reasoning Models via LoRA☆266Updated last month
- Survey of Small Language Models from Penn State, ...☆185Updated last month
- An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]☆329Updated last year