OpenLMLab / MOSS-RLHFLinks
Secrets of RLHF in Large Language Models Part I: PPO
☆1,384Updated last year
Alternatives and similar repositories for MOSS-RLHF
Users that are interested in MOSS-RLHF are comparing it to the libraries listed below
Sorting:
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,512Updated last year
- Recipes to train reward model for RLHF.☆1,418Updated 3 months ago
- [NIPS2023] RRHF & Wombat☆811Updated last year
- ☆908Updated last year
- A recipe for online RLHF and online iterative DPO.☆524Updated 7 months ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,032Updated 2 years ago
- Open Academic Research on Improving LLaMA to SOTA LLM☆1,619Updated last year
- ☆920Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆821Updated last year
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆912Updated 5 months ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,678Updated 11 months ago
- Aligning Large Language Models with Human: A Survey☆731Updated last year
- ☆544Updated 7 months ago
- Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)☆2,674Updated 11 months ago
- ☆758Updated last year
- Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"☆1,184Updated last year
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,816Updated 7 months ago
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆769Updated 2 years ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,766Updated last month
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆977Updated 7 months ago
- Panda项目是于2023年5月启动的开源海外中文大语言模型项目,致力于大模型时代探索整个技术栈,旨在推动中文自然语言处理领域的创新和合作。☆1,038Updated last year
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆561Updated 7 months ago
- AgentTuning: Enabling Generalized Agent Abilities for LLMs☆1,454Updated last year
- LOMO: LOw-Memory Optimization☆989Updated last year
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆654Updated 6 months ago
- We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tunin…☆2,761Updated last year
- The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".☆1,548Updated 2 months ago
- Collaborative Training of Large Language Models in an Efficient Way☆417Updated 11 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,805Updated 6 months ago
- minimal-cost for training 0.5B R1-Zero☆763Updated 2 months ago