Jannoshh

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

geometry-of-truth

github2file

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

llms-as-optimizers

Using LLMs to optimize

nanoGCG

A fast + lightweight implementation of the GCG algorithm in PyTorch

simple-sam

Sharpness-Aware Minimization for Efficiently Improving Generalization

Jannoshh/simple-sam

Sharpness-Aware Minimization for Efficiently Improving Generalization

Jannoshh/cheatsheets

Jannoshh/clean-llamas

Clean version of the Llama transformer architecture.

Jannoshh/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.

Jannoshh/DeepRL

Jannoshh/geometry-of-truth

Jannoshh/github2file

Jannoshh/llm-attacks

Universal and Transferable Attacks on Aligned Language Models

Jannoshh/llms-as-optimizers

Using LLMs to optimize

Jannoshh/nanoGCG

A fast + lightweight implementation of the GCG algorithm in PyTorch

Jannoshh/Password-Locked-LLM

Jannoshh/promptbase

All things prompt engineering

Jannoshh/superposition

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