openpsi-project / ReaLHFLinks
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆330Updated 8 months ago
Alternatives and similar repositories for ReaLHF
Users that are interested in ReaLHF are comparing it to the libraries listed below
Sorting:
- A flexible and efficient training framework for large-scale alignment tasks☆447Updated 2 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆283Updated 2 months ago
- Training library for Megatron-based models with bi-directional Hugging Face conversion capability☆363Updated this week
- ☆209Updated 2 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆183Updated last week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆280Updated 11 months ago
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆249Updated 9 months ago
- Async pipelined version of Verl☆124Updated 9 months ago
- (best/better) practices of megatron on veRL and tuning guide☆120Updated 3 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆688Updated last year
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆191Updated 10 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆98Updated 4 months ago
- ☆327Updated 7 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆484Updated this week
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆402Updated 3 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆350Updated last week
- A Comprehensive Survey on Long Context Language Modeling☆215Updated last month
- ☆328Updated 7 months ago
- The related works and background techniques about Openai o1☆221Updated last year
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆409Updated 6 months ago
- A version of verl to support diverse tool use☆819Updated 2 weeks ago
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆199Updated 2 years ago
- ☆66Updated last year
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆261Updated last month
- ☆214Updated 11 months ago
- Reproducing R1 for Code with Reliable Rewards☆280Updated 8 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆370Updated last year
- Deepseek R1 zero tiny version own reproduce on two A100s.☆82Updated 11 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆626Updated this week
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆116Updated 5 months ago