ADA-research / VERONALinks
A lightweight Python package for setting up adversarial robustness experiments and to compute robustness distributions. The package implements adversarial attacks which can be extended with the auto-verify plugin to enable complete verification.
☆36Updated last week
Alternatives and similar repositories for VERONA
Users that are interested in VERONA are comparing it to the libraries listed below
Sorting:
- Interpretability for sequence generation models 🐛 🔍☆439Updated last week
- Mediterranean Machine Learning school 2025 tutorials☆33Updated last week
- The website for Danish Foundation Models, a project for training foundational Danish language model.☆74Updated last month
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆665Updated last week
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆102Updated 8 months ago
- ☆359Updated last week
- A framework for conducting machine learning experiments in python☆41Updated 9 months ago
- ☆81Updated 7 months ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- The most extensive open massively multilingual corpus of datasets for training sentiment models. The corpus consists of 79 manually selec…☆16Updated last year
- Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning)…☆270Updated this week
- A Scandinavian Benchmark for sentence embeddings☆41Updated 4 months ago
- Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations☆624Updated 2 months ago
- Repository for TabICL: A Tabular Foundation Model for In-Context Learning on Large Data☆180Updated last month
- ☆21Updated 8 months ago
- Unified access to Large Language Model modules using NNsight☆47Updated last week
- Efficient optimizers☆261Updated this week
- Implementation of https://srush.github.io/annotated-s4☆502Updated 3 months ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆220Updated 9 months ago
- The robust European language model benchmark.☆125Updated this week
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆810Updated 3 weeks ago
- ☆16Updated last month
- Benchmark to Evaluate EXplainable AI☆20Updated 6 months ago
- Reliable, minimal and scalable library for pretraining foundation and world models☆63Updated this week
- Modalities, a PyTorch-native framework for distributed and reproducible foundation model training.☆85Updated last week
- ☆242Updated 11 months ago
- ☆345Updated last month
- ☆68Updated 2 years ago
- A list of awesome open source projects in the machine learning field, who's developers are mainly based in Germany☆46Updated last year