firstuserhere
Taking apart neural networks and putting them back together for a living. Personal website: https://kunvarthaman.com
firstuserhere's Stars
aseichter2007/ClipboardConqueror
Clipboard Conqueror is a novel copy and paste copilot alternative designed to bring your very own LLM AI assistant to any text field.
Vaibhavs10/insanely-fast-whisper
pbelcak/fastfeedforward
A repository for log-time feedforward networks
hediet/vscode-debug-visualizer
An extension for VS Code that visualizes data during debugging.
state-spaces/mamba
Mamba SSM architecture
spfrommer/torchexplorer
Interactively inspect module inputs, outputs, parameters, and gradients.
srush/GPU-Puzzles
Solve puzzles. Learn CUDA.
facebookresearch/ijepa
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
openai/weak-to-strong
loganriggs/sparse_coding
guoqincode/Open-AnimateAnyone
Unofficial Implementation of Animate Anyone
magic-research/magic-animate
[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
ml-explore/mlx
MLX: An array framework for Apple silicon
cbh123/narrator
David Attenborough narrates your life
Xmaster6y/devinterp
Tools for studying developmental interpretability in neural networks.
machine-discovery/deer
Parallelizing non-linear sequential models over the sequence length
timaeus-research/devinterp
Tools for studying developmental interpretability in neural networks.
MinghuiChen43/awesome-trustworthy-deep-learning
A curated list of trustworthy deep learning papers. Daily updating...
BuilderIO/gpt-crawler
Crawl a site to generate knowledge files to create your own custom GPT from a URL
ai-safety-foundation/sparse_autoencoder
Sparse Autoencoder for Mechanistic Interpretability
HoagyC/sparse_coding
Using sparse coding to find distributed representations used by neural networks.
nrimsky/CAA
Steering Llama 2 with Contrastive Activation Addition
Baidicoot/easy-sae-training
Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.
andyzoujm/representation-engineering
Representation Engineering: A Top-Down Approach to AI Transparency
NaNoGenMo/2023
National Novel Generation Month, 2023 edition.
eylonmiz/react-agent
The open-source React.js Autonomous LLM Agent
firstuserhere/gpt4Vadvanced
Testing GPT-4 Vision on Advanced examination questions (2023) across physics, chemistry, and mathematics
firstuserhere/firstuserhere_test.github.io
Cveinnt/LiveTerm
💻 Build terminal styled websites in minutes!
edwardjhu/TP4
Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)