openpsi-project / ReaLHFLinks
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆306Updated 2 months ago
Alternatives and similar repositories for ReaLHF
Users that are interested in ReaLHF are comparing it to the libraries listed below
Sorting:
- slime is a LLM post-training framework aiming for RL Scaling.☆596Updated this week
- A flexible and efficient training framework for large-scale alignment tasks☆388Updated this week
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 3 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆370Updated last week
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆136Updated this week
- ☆193Updated 3 months ago
- Scalable toolkit for efficient model reinforcement☆499Updated this week
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆652Updated 5 months ago
- Async pipelined version of Verl☆106Updated 3 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆188Updated 3 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆574Updated last week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆228Updated 4 months ago
- Repository of LV-Eval Benchmark☆67Updated 10 months ago
- Reproducing R1 for Code with Reliable Rewards☆232Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆459Updated 11 months ago
- ☆303Updated last month
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆528Updated last month
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆278Updated last week
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆341Updated 9 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆224Updated this week
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆412Updated last month
- The related works and background techniques about Openai o1☆223Updated 6 months ago
- ☆205Updated 4 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆194Updated 5 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆249Updated last month
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆421Updated 8 months ago
- ☆64Updated 7 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆215Updated 3 weeks ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆205Updated 7 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆226Updated 2 months ago