mansheej / icl-task-diversityLinks
Code for the paper "Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression"
☆25Updated 2 years ago
Alternatives and similar repositories for icl-task-diversity
Users that are interested in icl-task-diversity are comparing it to the libraries listed below
Sorting:
- ☆63Updated 4 years ago
- ☆34Updated 2 years ago
- ☆73Updated last year
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆105Updated 2 years ago
- ☆114Updated 11 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆177Updated 7 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated 2 years ago
- The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We…☆46Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated 2 years ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆20Updated last year
- Efficient empirical NTKs in PyTorch☆22Updated 3 years ago
- ☆76Updated 3 years ago
- ☆241Updated last year
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations☆30Updated 5 years ago
- ☆32Updated last year
- ☆33Updated 11 months ago
- ☆19Updated 2 years ago
- ☆31Updated 10 months ago
- ☆80Updated 3 years ago
- ☆84Updated 2 years ago
- Official Repository for ICML 2023 paper "Can Neural Network Memorization Be Localized?"☆20Updated 2 years ago
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆104Updated this week
- ☆114Updated 3 years ago
- ☆53Updated last year
- A library for efficient patching and automatic circuit discovery.☆86Updated last month
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆99Updated 4 years ago
- A centralized place for deep thinking code and experiments☆90Updated 2 years ago
- A fast, effective data attribution method for neural networks in PyTorch☆227Updated last year
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆106Updated 5 years ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆42Updated 11 months ago