Alternatives and similar repositories for Online-RLHF:

Users that are interested in Online-RLHF are comparing it to the libraries listed below

• RLHFlow / RLHF-Reward-Modeling
  Recipes to train reward model for RLHF.
  ☆1,290Updated 2 months ago
• THUDM / ReST-MCTS
  ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)
  ☆613Updated 3 months ago
• allenai / reward-bench
  RewardBench: the first evaluation tool for reward models.
  ☆553Updated last month
• princeton-nlp / SimPO
  [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
  ☆873Updated 2 months ago
• uclaml / SPPO
  The official implementation of Self-Play Preference Optimization (SPPO)
  ☆531Updated 2 months ago
• MARIO-Math-Reasoning / Super_MARIO
  ☆326Updated 2 months ago
• meta-math / MetaMath
  MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
  ☆428Updated last year
• princeton-nlp / LESS
  [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning
  ☆431Updated 6 months ago
• OpenLMLab / MOSS-RLHF
  Secrets of RLHF in Large Language Models Part I: PPO
  ☆1,356Updated last year
• YuxiXie / MCTS-DPO
  This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.
  ☆303Updated 8 months ago
• Ledzy / BAdam
  [NeurIPS 2024] BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
  ☆252Updated last month
• RLHFlow / Online-DPO-R1
  Codebase for Iterative DPO Using Rule-based Rewards
  ☆237Updated last week
• dvlab-research / Step-DPO
  Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
  ☆359Updated 3 months ago
• eddycmu / demystify-long-cot
  ☆282Updated last month
• RUCAIBox / Slow_Thinking_with_LLMs
  A series of technical report on Slow Thinking with LLM
  ☆630Updated last week
• hkust-nlp / deita
  Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
  ☆546Updated 4 months ago
• lqtrung1998 / mwp_ReFT
  ☆516Updated 3 months ago
• OpenBMB / UltraFeedback
  A large-scale, fine-grained, diverse preference dataset (and models).
  ☆336Updated last year
• sail-sg / oat-zero
  A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.
  ☆223Updated this week
• huggingface / Math-Verify
  ☆630Updated 3 weeks ago
• RLHFlow / Self-rewarding-reasoning-LLM
  Recipes to train the self-rewarding reasoning LLMs.
  ☆212Updated last month
• GAIR-NLP / LIMR
  ☆185Updated 2 months ago
• FranxYao / Long-Context-Data-Engineering
  Implementation of paper Data Engineering for Scaling Language Models to 128K Context
  ☆458Updated last year
• sangmichaelxie / doremi
  Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets
  ☆320Updated last year
• cmu-l3 / l1
  L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  ☆190Updated last month
• OpenBMB / Eurus
  ☆314Updated 7 months ago
• voidism / DoLa
  Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
  ☆480Updated 3 months ago
• magpie-align / magpie
  [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …
  ☆676Updated last month
• ZubinGou / math-evaluation-harness
  A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨
  ☆199Updated 11 months ago
• vwxyzjn / lm-human-preference-details
  RLHF implementation details of OAI's 2019 codebase
  ☆186Updated last year