maxlampe

tacheles

a lightweight, open-source blueprint for building powerful and scalable LLM chat applications

PurpleLlama

Set of tools to assess and improve LLM security.

trl

Train transformer language models with reinforcement learning.

TransformerLens

A library for mechanistic interpretability of GPT-style language models

virgo

Variational Inference package for unsupeRvised classification of (inter-)Galactic shOck waves

acronym

ACRONYM (Acronym CReatiON for You and Me)

causalbackdoor

Code for backdoor paper

Fine-pruning-defense

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)

trojan-lm

TrojanLM: Trojaning Language Models for Fun and Profit

Revise.jl

Automatically update function definitions in a running Julia session

pyfof

Friends of Friends cluster finding in python.

Differentiable-DAG-Sampling

Differentiable DAG Sampling (ICLR 2022)

classroom

Preference-based reinforcement learning in PyTorch and JAX with a browser-based GUI.

ReinforcementLearning.jl

A reinforcement learning package for Julia

BeautifulAlgorithms.jl

Concise and beautiful algorithms written in Julia

CancerClassificationProject.jl

panter

Perkeo ANalysis Tool for Evaluation and Reduction - is a data analysis framework for PERKEO III data.

NobleAD

Neutron beam line setup with automatic differentiation

HEBO

Bayesian optimisation & Reinforcement Learning library developped by Huawei Noah's Ark Lab

SPHKernels.jl

Julia implementation of some common SPH kernels

tomopt

TomOpt: Differential Muon Tomography Optimisation

texprlcount

Perl script that evaluates the word count of a tex document according to the PRL length guidelines