MadryLab / trak
A fast, effective data attribution method for neural networks in PyTorch
☆204Updated 4 months ago
Alternatives and similar repositories for trak:
Users that are interested in trak are comparing it to the libraries listed below
- Data for "Datamodels: Predicting Predictions with Training Data"☆96Updated last year
- AI Logging for Interpretability and Explainability🔬☆111Updated 10 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆144Updated 8 months ago
- A simple PyTorch implementation of influence functions.☆85Updated 10 months ago
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆71Updated last week
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆77Updated last year
- ☆60Updated 3 years ago
- ☆66Updated 3 years ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆63Updated 6 months ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆101Updated last year
- ☆83Updated this week
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆105Updated last year
- ☆91Updated 2 months ago
- ☆93Updated last year
- ☆54Updated 2 years ago
- Conformal Language Modeling☆28Updated last year
- ☆43Updated 5 months ago
- ☆28Updated last year
- A library for efficient patching and automatic circuit discovery.☆62Updated 2 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆40Updated 2 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆96Updated last month
- ☆225Updated 11 months ago
- Official repository for CMU Machine Learning Department's 10732: Robustness and Adaptivity in Shifting Environments☆73Updated 2 years ago
- Efficient empirical NTKs in PyTorch☆18Updated 2 years ago
- ☆29Updated 9 months ago
- ☆201Updated last year
- ☆47Updated last year
- OpenDataVal: a Unified Benchmark for Data Valuation in Python (NeurIPS 2023)☆95Updated 2 months ago
- [NeurIPS 2021] WRENCH: Weak supeRvision bENCHmark☆224Updated last year
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆71Updated 11 months ago