Download
MiniOneRec is an open-source framework designed to explore generative approaches to recommendation systems using large language model architectures. Traditional recommender systems typically rely on large embedding tables and ranking models, but MiniOneRec adopts a generative paradigm in which items are represented as sequences of semantic identifiers generated by autoregressive models. The framework provides an end-to-end pipeline for building generative recommender systems, including semantic identifier construction, supervised fine-tuning, and reinforcement learning-based optimization. Semantic IDs are created using techniques such as quantized variational autoencoders to convert item features into token sequences that can be modeled by transformer architectures. Developers can train and evaluate recommendation models using different backbone language models while benefiting from the generative framework’s parameter efficiency and scalability.
Features
- End-to-end generative recommendation framework using transformer models
- Semantic identifier construction for representing items as token sequences
- Supervised fine-tuning pipelines for recommendation models
- Reinforcement learning optimization for recommendation performance
- Support for multiple backbone language models and datasets
- Evaluation tools for ranking accuracy and recommendation diversity
Project Samples
