
SimPO
by princeton-nlp (organization)
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward (description from the project’s GitHub page)
Repository facts
- Stars
- 962
- Forks
- 78
- Open issues and pull requests
- 25
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- princeton-nlp · Organization
- Created
- May 21, 2024
- Last push
- Feb 16, 2025
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 4,750: OpenLMLab/MOSS-RLHF
Secrets of RLHF in Large Language Models Part I: PPO
1,427 starsPythonApache-2.0Last push Mar 3, 2024
Rank 6,648: agentscope-ai/OpenJudge
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
877 starsPythonApache-2.0Last push Sep 11, 2026
Rank 8,254: RobustNLP/CipherChat
A framework to evaluate the generalization capability of safety alignment for LLMs
630 starsPythonMITLast push Oct 9, 2025
Rank 8,465: hkust-nlp/deita
Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
606 starsPythonApache-2.0Last push Dec 9, 2024
Rank 64: hiyouga/LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
75,561 starsPythonApache-2.0Last push Oct 10, 2026
Rank 658: RUCAIBox/LLMSurvey
The official GitHub page for the survey paper "A Survey of Large Language Models".
12,233 starsPythonNo license file detectedLast push Mar 11, 2025