epfml / getting-started
☆19Updated 3 months ago
Alternatives and similar repositories for getting-started:
Users that are interested in getting-started are comparing it to the libraries listed below
- Relative representations can be leveraged to enable solving tasks regarding "latent communication": from zero-shot model stitching to lat…☆56Updated last year
- Model zoo for different kinds of uncertainty quantification methods used in Natural Language Processing, implemented in PyTorch.☆51Updated last year
- Efficient empirical NTKs in PyTorch☆18Updated 2 years ago
- A convenient way to trigger synchronizations to wandb / Weights & Biases if your compute nodes don't have internet!☆70Updated 2 weeks ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆40Updated 2 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆38Updated 4 months ago
- ☆86Updated last week
- Official implementation of "Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks", NeurIPS 2021.☆31Updated 3 years ago
- ☆16Updated last year
- nanoGPT-like codebase for LLM training☆89Updated this week
- ☆11Updated last year
- ☆64Updated 2 years ago
- ☆52Updated this week
- Using sparse coding to find distributed representations used by neural networks.☆213Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆192Updated 3 months ago
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆39Updated 3 months ago
- ☆63Updated 2 months ago
- ☆22Updated last year
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆26Updated 9 months ago
- ☆17Updated 8 months ago
- Lightweight Adapting for Black-Box Large Language Models☆19Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆29Updated 8 months ago
- ☆205Updated 4 months ago
- [ICML 2022] Representation Topology Divergence: A Method for Comparing Neural Network Representations☆19Updated 2 years ago
- ☆109Updated 6 months ago
- Official source code for "Graph Neural Networks for Learning Equivariant Representations of Neural Networks". In ICLR 2024 (oral).☆77Updated 6 months ago
- "Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)☆84Updated last year
- Conformal Language Modeling☆28Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆95Updated last year
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆62Updated last week