TRAIS-Lab / dattriLinks
`dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.
☆93Updated last week
Alternatives and similar repositories for dattri
Users that are interested in dattri are comparing it to the libraries listed below
Sorting:
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆76Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆221Updated 11 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆167Updated 4 months ago
- AI Logging for Interpretability and Explainability🔬☆133Updated last year
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆83Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆83Updated 8 months ago
- A simple PyTorch implementation of influence functions.☆91Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated 2 weeks ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆106Updated 2 years ago
- ☆101Updated 2 years ago
- ☆241Updated last year
- ☆109Updated 9 months ago
- This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).☆51Updated last year
- ☆78Updated 3 years ago
- ☆52Updated 7 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆183Updated 6 months ago
- ☆60Updated 3 months ago
- ☆51Updated last year
- ☆31Updated last year
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆29Updated last year
- A library for efficient patching and automatic circuit discovery.☆79Updated 3 months ago
- ☆29Updated 9 months ago
- [ICLR 2025] General-purpose activation steering library☆116Updated last month
- ☆102Updated last year
- ☆134Updated 3 weeks ago
- ☆237Updated last year
- ☆46Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆140Updated 4 months ago
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆48Updated 5 months ago
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆82Updated 10 months ago