TamSiuhin/OPPU
Official Implementation of "Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning" at EMNLP 2024 Main Conference
This project helps you create large language models that deeply understand and adapt to individual user preferences and behaviors without sacrificing privacy. By taking user interaction data and profiles, it produces a highly personalized model that delivers more relevant content, recommendations, or responses. This is ideal for product managers or researchers focused on enhancing user experience and engagement in AI applications.
No commits in the last 6 months.
Use this if you need to personalize LLM interactions for many users while maintaining data privacy and accurately capturing their evolving preferences.
Not ideal if your application requires a general-purpose LLM without individual user customization or if you're comfortable with centralized data processing.
Stars
44
Forks
4
Language
Python
License
—
Category
Last pushed
Jul 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TamSiuhin/OPPU"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scaleapi/llm-engine
Scale LLM Engine public repository
AGI-Arena/MARS
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
modelscope/easydistill
a toolkit on knowledge distillation for large language models
AGI-Edgerunners/LLM-Adapters
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient...
Wang-ML-Lab/bayesian-peft
Bayesian Low-Rank Adaptation of LLMs: BLoB [NeurIPS 2024] and TFB [NeurIPS 2025]