AkaliKong/MiniOneRec
An open-source framework for building and training generative recommendation systems using large language models.
Not currently ranked — collecting fresh signals.
star history
MiniOneRec provides an end-to-end workflow for generative recommendation using LLMs, spanning SID construction, supervised fine-tuning (SFT), and recommendation-oriented reinforcement learning (RL). It enables training language models to directly generate recommendation items rather than using traditional ranking paradigms. The framework supports constrained decoding and evaluation metrics specific to generative recommendation tasks.
Frequently asked
- What is AkaliKong/MiniOneRec?
- An open-source framework for building and training generative recommendation systems using large language models.
- Is MiniOneRec open source?
- Yes — AkaliKong/MiniOneRec is open source, released under the Apache-2.0 license.
- What language is MiniOneRec written in?
- AkaliKong/MiniOneRec is primarily written in Python.
- How popular is MiniOneRec?
- AkaliKong/MiniOneRec has 1.7k stars on GitHub.
- Where can I find MiniOneRec?
- AkaliKong/MiniOneRec is on GitHub at https://github.com/AkaliKong/MiniOneRec.