openpsi-project / ReaLHF
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
☆85Updated this week
Related projects: ⓘ
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆89Updated 2 months ago
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆141Updated 9 months ago
- ☆98Updated 2 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆101Updated last month
- Official implementation for the paper *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆57Updated 3 weeks ago
- Official github repo for the paper "Compression Represents Intelligence Linearly"☆121Updated 3 months ago
- RLHF implementation details of OAI's 2019 codebase☆144Updated 8 months ago
- Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied wit…☆61Updated 2 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆183Updated last month
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search☆91Updated 3 months ago
- Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning☆176Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆309Updated this week
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆244Updated last week
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆158Updated 4 months ago
- ☆79Updated 3 months ago
- ☆24Updated 6 months ago
- [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”☆114Updated 2 months ago
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆208Updated last week
- Align Anything: Training All-modality Model with Feedback☆100Updated last week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting☆60Updated 6 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆84Updated 5 months ago
- Achieving Efficient Alignment through Learned Correction☆103Updated 3 months ago
- ☆179Updated last week
- Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards"☆22Updated 2 months ago
- ☆164Updated 4 months ago
- Paper collections of the continuous effort start from World Models.☆127Updated 2 months ago
- AI Alignment: A Comprehensive Survey☆123Updated 10 months ago
- [ACL'2024] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆44Updated last month
- ☆29Updated last month
- [NeurIPS 2023] Large Language Models Are Semi-Parametric Reinforcement Learning Agents☆31Updated 4 months ago