chrisliu298 Goto Github PK

adversarial-sample-complexity

We show that adversarially training (Fast Gradient Sign Method and Projected Gradient Descent) reduces the empirically sample complexity rate for MLP and a variety of CNN architectures on MNIST and CIFAR-10.

alignment-handbook

Robust recipes to align language models with human and AI preferences

amazon-product-recommendation

arxiv_dataset

I use the titles and abstract of these papers to fine-tune my GPT-2 model.

awesome-genai-unlearning

awesome-llm-unlearning

A resource repository for machine unlearning in large language models

awesome-representation-engineering

A resource repository for representation engineering in large language models

awesome-sparse-autoencoders

A resource repository of sparse autoencoders for large language models

bert-glue

chrisliu298

cifar-baseline

I train several models as baseline on CIFAR-10 and CIFAR-100.

cifar10-unlearn

circuit-breakers

Improving Alignment and Robustness with Circuit Breakers

comvex

Learning to construct compact representations of neural network weight matrices by linearly projecting them into a smaller space

conda-config

connect_four_features

copilot.vim

Neovim plugin for GitHub Copilot

cv_emulate

Academic CVs that you can emulate

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

firefoxcss

Oneline, minimal, keyboard-centered Firefox CSS theme.

gpt2-arxiv

Fine-tuning GPT-2 to generate research paper abstracts

halu_clf

hugo-website

Minimalist Hugo template for academic websites

ib-double-descent

imagenette-baseline

imdb-baseline

keras

Deep Learning for humans

kickstart.nvim

A launch point for your personal nvim configuration

llm-unlearn-eco

Code for Large Language Model Unlearning via Embedding-Corrupted Prompts

max-margin