#direct-preference-optimization Repositories
Discover 11 active open source GitHub repositories tagged with #direct-preference-optimization, accumulating 41,696 total stars (averaging 3,790 stars per project). Leading this topic is huggingface/trl with 19,788 stars.
11 repositories total
Reference implementation for DPO (Direct Preference Optimization)
This is a project to train large language models from scratch, including pre-training, fine-tuning, and direct preference optimization, with the model having 1B parameters and supporting Chinese and English.
Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think & UnifiedReward-Flex
Code for "Diffusion Model Alignment Using Direct Preference Optimization"
Frequently Asked Questions
What is the most popular #direct-preference-optimization repository on GitHub?
The top ranked open source #direct-preference-optimization project on GitHub is huggingface/trl with 19,788 stars. Train transformer language models with reinforcement learning.
Which programming languages are most used in #direct-preference-optimization repositories?
Among the top ranked #direct-preference-optimization projects on GitHub, the most common programming languages are Python.
How is the #direct-preference-optimization repository ranking calculated?
We track 11 active open source repositories tagged with #direct-preference-optimization (500+ stars), totaling 41,696 stars with an average of 3,790 stars per repository. Rankings update daily from the GitHub API.