openpsi-project / ReaLHFLinks
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆323Updated 6 months ago
Alternatives and similar repositories for ReaLHF
Users that are interested in ReaLHF are comparing it to the libraries listed below
Sorting:
- ☆203Updated 6 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆261Updated 3 weeks ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆142Updated this week
- A flexible and efficient training framework for large-scale alignment tasks☆433Updated this week
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆247Updated 6 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆369Updated this week
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆673Updated 9 months ago
- Async pipelined version of Verl☆121Updated 6 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆222Updated this week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆260Updated 8 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆189Updated 7 months ago
- ☆323Updated 4 months ago
- (best/better) practices of megatron on veRL and tuning guide☆94Updated last month
- A version of verl to support diverse tool use☆627Updated this week
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆305Updated last month
- A Comprehensive Survey on Long Context Language Modeling☆193Updated 3 months ago
- ☆300Updated 5 months ago
- The related works and background techniques about Openai o1☆222Updated 9 months ago
- ☆211Updated 8 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆348Updated 3 weeks ago
- Ring attention implementation with flash attention☆903Updated last month
- Reproducing R1 for Code with Reliable Rewards☆259Updated 5 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆440Updated last year
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆352Updated last year
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆249Updated 3 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆258Updated 5 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆259Updated last year
- ☆342Updated 4 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆112Updated 2 months ago
- Repository of LV-Eval Benchmark☆70Updated last year