1 repo
Awesome GitHub RepositoriesPreference Optimization
Algorithms for aligning model outputs with human preferences directly without separate reward model training.
Distinguishing note: Focuses on direct alignment methods like DPO rather than traditional multi-stage RLHF.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Preference Optimization. Refine with filters or upvote what's useful.
Awesome Preference Optimization GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- jingyaogong/minimind
jingyaogong/minimind
39,663View on GitHubThis project is a comprehensive framework for the entire lifecycle of transformer-based language models, supporting everything from foundational pretraining to specialized deployment. It provides a modular toolkit for defining neural network architectures, managing data preparation pipelines, and executing training routines across various scales. The framework is designed to handle the full model development process, including supervised fine-tuning, behavioral alignment, and the integration of agentic capabilities. What distinguishes this framework is its focus on efficient training and adva
The framework enables preference optimization to align model responses with human preferences, improving output quality without the need for complex, separate reward models.
Pythonartificial-intelligencelarge-language-model
