openpsi-project / ReaLHFLinks
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆322Updated 6 months ago
Alternatives and similar repositories for ReaLHF
Users that are interested in ReaLHF are comparing it to the libraries listed below
Sorting:
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆268Updated last week
- A flexible and efficient training framework for large-scale alignment tasks☆437Updated 3 weeks ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆398Updated this week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆264Updated 8 months ago
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆248Updated 7 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆149Updated last week
- ☆205Updated 2 weeks ago
- Async pipelined version of Verl☆125Updated 7 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆224Updated this week
- (best/better) practices of megatron on veRL and tuning guide☆99Updated last month
- Training library for Megatron-based models☆174Updated this week
- A version of verl to support diverse tool use☆668Updated last week
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 7 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆678Updated 9 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆318Updated last month
- ☆309Updated 5 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆364Updated last month
- ☆326Updated 5 months ago
- ☆212Updated 8 months ago
- A Comprehensive Survey on Long Context Language Modeling☆199Updated 4 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆251Updated 4 months ago
- The related works and background techniques about Openai o1☆221Updated 10 months ago
- Reproducing R1 for Code with Reliable Rewards☆267Updated 6 months ago
- 青稞Talk☆160Updated last week
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆170Updated 2 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆258Updated 6 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆75Updated 2 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆639Updated 3 weeks ago
- A series of technical report on Slow Thinking with LLM☆743Updated 3 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆114Updated 3 months ago