Jannes Elstner's repositories
simple-sam
Sharpness-Aware Minimization for Efficiently Improving Generalization
clean-llamas
Clean version of the Llama transformer architecture.
Language:Python000
deep_residual_voxel_autoencoder
In the domain of computer vision, deep residual neural networks like EfficientNet have set new standards in terms of robustness and accuracy. In this work, we present a deep residual 3D autoencoder based on the EfficientNet architecture for transfer learning. For this purpose, we adopted EfficientNet to 3D problems like voxel models derived from a STEP file.
Language:Python000
Language:Python000
Language:Python000
llms-as-optimizers
Using LLMs to optimize
Language:Python000
promptbase
All things prompt engineering
Language:PythonMIT000
superposition
Replicating Toy Models of Superposition https://transformer-circuits.pub/2022/toy_model/index.html