Jannoshh

simple-sam

Sharpness-Aware Minimization for Efficiently Improving Generalization

cheatsheets

clean-llamas

Clean version of the Llama transformer architecture.

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.

DeepRL

github2file

llms-as-optimizers

Using LLMs to optimize

Password-Locked-LLM

promptbase

All things prompt engineering

superposition

Replicating Toy Models of Superposition https://transformer-circuits.pub/2022/toy_model/index.html