openpsi-project / ReaLHF
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆219Updated last month
Alternatives and similar repositories for ReaLHF:
Users that are interested in ReaLHF are comparing it to the libraries listed below
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆424Updated this week
- A flexible and efficient training framework for large-scale alignment tasks☆303Updated last week
- Repo of paper "Free Process Rewards without Process Labels"☆123Updated last month
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆192Updated 2 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆289Updated 6 months ago
- ☆319Updated 2 weeks ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆205Updated 6 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆307Updated 4 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆573Updated last month
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆223Updated 3 months ago
- adds Sequence Parallelism into LLaMA-Factory☆154Updated this week
- ☆220Updated 9 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆245Updated 2 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆172Updated 9 months ago
- Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied wit…☆114Updated 7 months ago
- RLHF implementation details of OAI's 2019 codebase☆178Updated last year
- The related works and background techniques about Openai o1☆210Updated last month
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆153Updated 2 months ago
- ☆57Updated 2 months ago
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆173Updated last year
- A series of technical report on Slow Thinking with LLM☆409Updated last week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆160Updated last week
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆420Updated 6 months ago
- A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to…☆55Updated last year
- Repository of LV-Eval Benchmark☆58Updated 5 months ago
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆245Updated 5 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆145Updated 8 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆84Updated 4 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆306Updated 2 weeks ago