Aly Mostafa's repositories
Instruction_based_attack
Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
DeMemorization
[EMNLP 2023] Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models
arabic-stop-words
Largest list of Arabic stop words on Github. أكبر قائمة لمستبعدات الفهرسة العربية على جيت هاب
DeepCASE
Original implementation and resources of DeepCASE as in the S&P '22 paper
DeepLog
Pytorch Implementation of DeepLog.
emoji-regex
A regular expression to match all Emoji-only symbols as per the Unicode Standard.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
knowledge-unlearning
[ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models
llm-attacks
Universal and Transferable Attacks on Aligned Language Models
LMTracker
The repository implement the LMTracker model based on paper: LMTracker: Lateral movement path detection based on heterogeneous graph embedding
metaseq
Repo for external large-scale work
mimir
Python package for measuring memorization in LLMs.
notebooks
Notebooks using the Hugging Face libraries 🤗
OpenNMT-py
Open Source Neural Machine Translation in PyTorch
privacy
Library for training machine learning models with privacy for training data
scattertext
Beautiful visualizations of how language differs among document types.
scholarly
Retrieve author and publication information from Google Scholar in a friendly, Pythonic way
stweet
Advanced python library to scrap Twitter (tweets, users) from unofficial API, fully covered by integration tests
text-image-binarization
An implementation of the paper 'Efficient illumination compensation techniques for text images'
trl
Train transformer language models with reinforcement learning.
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)