RLHFlow / Online-RLHFLinks
A recipe for online RLHF and online iterative DPO.
☆525Updated 7 months ago
Alternatives and similar repositories for Online-RLHF
Users that are interested in Online-RLHF are comparing it to the libraries listed below
Sorting:
- Recipes to train reward model for RLHF.☆1,439Updated 4 months ago
- ☆227Updated 3 months ago
- MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models☆439Updated last year
- RewardBench: the first evaluation tool for reward models.☆628Updated 2 months ago
- The official implementation of Self-Play Preference Optimization (SPPO)☆577Updated 7 months ago
- [NeurIPS 2024] BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models☆266Updated 5 months ago
- The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.☆428Updated 3 weeks ago
- ☆339Updated 2 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆321Updated last year
- Recipes to train the self-rewarding reasoning LLMs.☆224Updated 5 months ago
- ☆312Updated 2 months ago
- A large-scale, fine-grained, diverse preference dataset (and models).☆347Updated last year
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆191Updated last year
- Codebase for Iterative DPO Using Rule-based Rewards☆256Updated 4 months ago
- Controllable Text Generation for Large Language Models: A Survey☆185Updated 11 months ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,394Updated last year
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆279Updated last year
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆913Updated 6 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆660Updated 7 months ago
- A series of technical report on Slow Thinking with LLM☆722Updated last week
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆765Updated this week
- ☆305Updated last year
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 4 months ago
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆376Updated 7 months ago
- ☆206Updated 6 months ago
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆267Updated 11 months ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆477Updated 10 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆248Updated 3 months ago
- ☆204Updated 5 months ago
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆341Updated last year