MadryLab / trakLinks
A fast, effective data attribution method for neural networks in PyTorch
☆220Updated 11 months ago
Alternatives and similar repositories for trak
Users that are interested in trak are comparing it to the libraries listed below
Sorting:
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆90Updated last week
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆83Updated last year
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆165Updated 4 months ago
- A simple PyTorch implementation of influence functions.☆91Updated last year
- ☆77Updated 3 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- AI Logging for Interpretability and Explainability🔬☆129Updated last year
- ☆240Updated last year
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆76Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆105Updated 2 years ago
- ☆62Updated 3 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆82Updated 7 months ago
- "Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)☆88Updated 2 years ago
- ☆107Updated 8 months ago
- Framework code with wandb, checkpointing, logging, configs, experimental protocols. Useful for fine-tuning models or training from scratc…☆151Updated 2 years ago
- ☆31Updated last year
- ☆102Updated last year
- ☆98Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆50Updated last year
- Conformal Language Modeling☆32Updated last year
- ☆28Updated 8 months ago
- ☆37Updated 10 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
- ☆58Updated 2 years ago
- ☆23Updated last year
- ☆131Updated last week
- ☆30Updated 2 years ago
- ☆234Updated last year
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 8 months ago