nsfzyzz / Generalization_metrics_for_NLPLinks
[KDD 2023] code for "Test accuracy vs. generalization gap: model selection in NLP without accessing training or testing data" https://arxiv.org/pdf/2202.02842.pdf
☆12Updated 3 years ago
Alternatives and similar repositories for Generalization_metrics_for_NLP
Users that are interested in Generalization_metrics_for_NLP are comparing it to the libraries listed below
Sorting:
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆175Updated 6 months ago
- Efficient empirical NTKs in PyTorch☆22Updated 3 years ago
- ☆241Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆227Updated last year
- ☆73Updated last year
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆100Updated this week
- This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).☆52Updated last year
- [NeurIPS 2021] code for "Taxonomizing local versus global structure in neural network loss landscapes" https://arxiv.org/abs/2107.11228☆19Updated 4 years ago
- A simple PyTorch implementation of influence functions.☆92Updated last year
- [NeurIPS 2023 Spotlight] Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training☆36Updated 9 months ago
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆84Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆108Updated 2 years ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆28Updated 2 years ago
- SGD with large step sizes learns sparse features [ICML 2023]☆33Updated 2 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 4 years ago
- Neural Tangent Kernel Papers☆120Updated 11 months ago
- A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...☆383Updated this week
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆63Updated 10 months ago
- LLM finetuning in resource-constrained environments.☆55Updated last year
- AI Logging for Interpretability and Explainability🔬☆138Updated last year
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆38Updated 3 years ago
- ☆20Updated last year
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆216Updated 3 weeks ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆79Updated last year
- Welcome to the 'In Context Learning Theory' Reading Group☆30Updated last year
- Minimal pretraining script for language modeling in PyTorch. Supporting torch compilation and DDP. It includes a model implementation and…☆42Updated last month
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆16Updated 6 years ago
- Code for steering and monitoring with concepts vectors in LLMs. https://arxiv.org/abs/2502.03708☆19Updated 5 months ago
- nanoGPT-like codebase for LLM training☆114Updated 2 months ago
- ☆34Updated last year