fletchel's Stars
TransformerLensOrg/TransformerLens
A library for mechanistic interpretability of GPT-style language models
krasheninnikov/internalization
Code for the paper "Implicit meta-learning may lead language models to trust more reliable sources"
robertdvdk/lico-fact
Repository for our project at the FACT-AI course. We will reproduce & extend the paper "LICO: Explainable Models with Language-Image Consistency", in the framework of the MLRC2023.
benchopt/benchopt
Making your benchmark of optimization algorithms simple and open
cabo40/pyrichlet
Data analysis library for Python using "Dirichlet Process"-based models.