pomonam / kronfluence
Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
β133Updated 6 months ago
Alternatives and similar repositories for kronfluence:
Users that are interested in kronfluence are comparing it to the libraries listed below
- AI Logging for Interpretability and Explainabilityπ¬β103Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.β53Updated this week
- β86Updated last week
- β109Updated 6 months ago
- Using sparse coding to find distributed representations used by neural networks.β213Updated last year
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.β61Updated last week
- β60Updated 3 years ago
- β116Updated last year
- β17Updated 2 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)β62Updated 4 months ago
- β203Updated 4 months ago
- A fast, effective data attribution method for neural networks in PyTorchβ192Updated 3 months ago
- nanoGPT-like codebase for LLM trainingβ89Updated this week
- Influence Analysis and Estimation - Survey, Papers, and Taxonomyβ69Updated 11 months ago
- A simple PyTorch implementation of influence functions.β84Updated 8 months ago
- Conformal Language Modelingβ28Updated last year
- β55Updated 3 months ago
- Sparse probing paper full code.β53Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Leβ¦β89Updated 3 years ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".β94Updated last year
- β171Updated last year
- β151Updated this week
- β21Updated 4 months ago
- β52Updated this week
- β190Updated 11 months ago
- β142Updated 3 weeks ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.β38Updated 4 months ago
- β211Updated 9 months ago
- β64Updated 2 years ago
- Code for the paper "Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression"β20Updated last year