Python package for measuring memorization in LLMs.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Universal and Transferable Attacks on Aligned Language Models

[ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Repo for external large-scale work

Library for training machine learning models with privacy for training data

Original implementation and resources of DeepCASE as in the S&P '22 paper

Train transformer language models with reinforcement learning.

The repository implement the LMTracker model based on paper: LMTracker: Lateral movement path detection based on heterogeneous graph embedding

Notebooks using the Hugging Face libraries 🤗

Pytorch Implementation of DeepLog.

An implementation of the paper 'Efficient illumination compensation techniques for text images'

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Largest list of Arabic stop words on Github. أكبر قائمة لمستبعدات الفهرسة العربية على جيت هاب

The fastai deep learning library

A regular expression to match all Emoji-only symbols as per the Unicode Standard.

Advanced python library to scrap Twitter (tweets, users) from unofficial API, fully covered by integration tests

Open Source Neural Machine Translation in PyTorch

Retrieve author and publication information from Google Scholar in a friendly, Pythonic way

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM)

Beautiful visualizations of how language differs among document types.

The BusTub Relational Database Management System (Educational)