openpsi-project / ReaLHF
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆281Updated 3 months ago
Alternatives and similar repositories for ReaLHF:
Users that are interested in ReaLHF are comparing it to the libraries listed below
- A flexible and efficient training framework for large-scale alignment tasks☆342Updated 2 months ago
- ☆179Updated last week
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆229Updated last week
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆297Updated 2 weeks ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆616Updated 3 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆173Updated last month
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆477Updated this week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆187Updated 2 months ago
- The related works and background techniques about Openai o1☆221Updated 3 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆197Updated 3 weeks ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆319Updated 7 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆438Updated 8 months ago
- ☆187Updated 2 months ago
- ☆283Updated last month
- ☆326Updated 2 months ago
- ☆647Updated 3 weeks ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆203Updated 11 months ago
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆181Updated last year
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆303Updated 8 months ago
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆256Updated 7 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆143Updated last month
- Ring attention implementation with flash attention☆743Updated 2 weeks ago
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks☆260Updated 8 months ago
- ☆698Updated this week
- Paper list for Efficient Reasoning.☆403Updated this week
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆191Updated last month
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆380Updated last week
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆107Updated this week
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆363Updated 3 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆184Updated last week