pomonam / kronfluenceLinks
Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
β153Updated 10 months ago
Alternatives and similar repositories for kronfluence
Users that are interested in kronfluence are comparing it to the libraries listed below
Sorting:
- AI Logging for Interpretability and Explainabilityπ¬β119Updated 11 months ago
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.β75Updated last month
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)β67Updated 8 months ago
- β97Updated last month
- A simple PyTorch implementation of influence functions.β88Updated 11 months ago
- A fast, effective data attribution method for neural networks in PyTorchβ211Updated 6 months ago
- β93Updated 3 months ago
- β121Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffingβ55Updated 7 months ago
- Influence Analysis and Estimation - Survey, Papers, and Taxonomyβ78Updated last year
- Efficient empirical NTKs in PyTorchβ18Updated 2 years ago
- β171Updated last month
- A library for efficient patching and automatic circuit discovery.β65Updated last month
- LLM finetuning in resource-constrained environments.β47Updated 11 months ago
- Using sparse coding to find distributed representations used by neural networks.β247Updated last year
- β43Updated 6 months ago
- β223Updated 8 months ago
- β83Updated 9 months ago
- Sparse probing paper full code.β56Updated last year
- β124Updated 6 months ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".β102Updated last year
- Conformal Language Modelingβ29Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.β72Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models β¦β181Updated this week
- β60Updated 3 years ago
- β117Updated 10 months ago
- β66Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).β200Updated 5 months ago
- β67Updated 3 years ago
- β302Updated 2 weeks ago