openpsi-project / ReaLHFLinks
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆319Updated 5 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.☆249Updated this week
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 5 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆428Updated this week
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆356Updated last week
- ☆202Updated 5 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆670Updated 8 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆130Updated last week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆256Updated 7 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆217Updated this week
- Async pipelined version of Verl☆117Updated 5 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 6 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆482Updated 3 weeks ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆310Updated 2 weeks ago
- (best/better) practices of megatron on veRL and tuning guide☆88Updated last week
- A version of verl to support diverse tool use☆570Updated this week
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆292Updated last week
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆162Updated last month
- A Comprehensive Survey on Long Context Language Modeling☆189Updated 2 months ago
- ☆211Updated 7 months ago
- ☆318Updated 4 months ago
- ☆297Updated 4 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆107Updated 2 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆46Updated 6 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆439Updated 11 months ago
- Reproducing R1 for Code with Reliable Rewards☆258Updated 5 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆248Updated 2 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆258Updated last year
- The related works and background techniques about Openai o1☆222Updated 8 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆337Updated 2 months ago
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆193Updated last year