openpsi-project / ReaLHF
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆237Updated 2 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☆322Updated last month
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆445Updated 3 weeks ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆197Updated 3 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆589Updated last month
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆238Updated this week
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆312Updated 5 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆132Updated this week
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 6 months ago
- The related works and background techniques about Openai o1☆216Updated 2 months ago
- Ring attention implementation with flash attention☆707Updated 2 weeks ago
- Repository of LV-Eval Benchmark☆59Updated 6 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆253Updated 3 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆392Updated 4 months ago
- ☆229Updated 10 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆171Updated last month
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆432Updated 7 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆293Updated 7 months ago
- ☆326Updated last month
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆164Updated 3 weeks ago
- ☆59Updated 3 months ago
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆175Updated last year
- A series of technical report on Slow Thinking with LLM☆536Updated this week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆150Updated 2 weeks ago
- RLHF implementation details of OAI's 2019 codebase☆183Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆331Updated last week
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆52Updated this week