Stars
Retrieves parquet files from Hugging Face, identifies and quantifies junky data, duplication, contamination, and biased content in dataset using pandas
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
AirLLM 70B inference with single 4GB GPU
中文langchain项目|小必应，Q.Talk，强聊，QiangTalk
Segment-Anything + 3D. Let's lift anything to 3D.
An index of algorithms for learning causality with data
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
StyleGAN-based predictor of children's faces from photos of theoretical parents.
This is the repository for our WSDM 2020 publication: Interpretable Click-through Rate Prediction through Hierarchical Attention