Steven's Projects
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
A collection of resources and papers on Diffusion Models
Reading list for research topics in multimodal machine learning
One-click deployment of many github open source projects to facilitate fast experience
🔊 Text-Prompted Generative Audio Model
Config files for my GitHub profile.
Master programming by recreating your favorite technologies from scratch.
Making large AI models cheaper, faster and more accessible
Let us control diffusion models!
Official electron build of draw.io
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Curated collection of human fingerprint datasets suitable for research and evaluation of fingerprint recognition algorithms.
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Release for Improved Denoising Diffusion Probabilistic Models
Config files for my GitHub profile.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
⚡ Building applications with LLMs through composability ⚡
Lantern官方版本下载 蓝灯 翻墙 代理 科学上网 外网 加速器 梯子 路由 proxy vpn circumvention gfw
Ongoing research training transformer models at scale
For familiarization with pandas
For familirization of torch
Clone a voice in 5 seconds to generate arbitrary speech in real-time
A game theoretic approach to explain the output of any machine learning model.
This is my Master's project that studies the spectral properties (eigenvalues and eigenvectors) of Hilbert-Schmidt integral operator which was applied on Gaussian processes induced by neural networks with infinitely many neurons in hidden layers.