MadryLab / trakLinks
A fast, effective data attribution method for neural networks in PyTorch
☆217Updated 9 months ago
Alternatives and similar repositories for trak
Users that are interested in trak are comparing it to the libraries listed below
Sorting:
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆82Updated last year
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆159Updated 2 months ago
- AI Logging for Interpretability and Explainability🔬☆125Updated last year
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆84Updated 2 months ago
- A simple PyTorch implementation of influence functions.☆90Updated last year
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆74Updated 10 months ago
- ☆238Updated last year
- ☆73Updated 3 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆76Updated 5 months ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆103Updated 2 years ago
- ☆60Updated 3 years ago
- This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).☆51Updated last year
- ☆57Updated 2 years ago
- ☆103Updated 6 months ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆108Updated last year
- ☆98Updated last year
- Conformal Language Modeling☆32Updated last year
- ☆96Updated last year
- ☆31Updated last year
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 6 months ago
- ☆50Updated last year
- ☆24Updated 6 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆53Updated 10 months ago
- Efficient empirical NTKs in PyTorch☆22Updated 3 years ago
- Framework code with wandb, checkpointing, logging, configs, experimental protocols. Useful for fine-tuning models or training from scratc…☆151Updated 2 years ago
- ☆36Updated 8 months ago
- ☆184Updated last month
- ☆47Updated last year
- Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"☆24Updated last year