Wang-ML-Lab/bayesian-peft
Bayesian Low-Rank Adaptation of LLMs: BLoB [NeurIPS 2024] and TFB [NeurIPS 2025]
This project offers methods for improving the reliability and performance of fine-tuned Large Language Models (LLMs). It takes an existing LLM adapter (like LoRA) and applies advanced Bayesian techniques to improve how well the model predicts new, unseen data and how confident those predictions are. This is useful for AI researchers and practitioners who want to develop more robust and trustworthy LLMs for various applications.
Use this if you are fine-tuning Large Language Models and need to improve their accuracy, calibration, and ability to generalize to new, out-of-distribution data.
Not ideal if you are looking for a basic LLM fine-tuning library or if you don't have a background in machine learning research.
Stars
35
Forks
5
Language
Python
License
MIT
Category
Last pushed
Feb 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Wang-ML-Lab/bayesian-peft"
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...
sangmichaelxie/doremi
Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language...