Stars
Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app
Triton implementation of Flash Attention2.0
Implementation of flash attention for educational purposes.
The Research Tree - A playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning.
Building modular LMs with parameter-efficient fine-tuning.
Configuration files and how-to instructions of utilities for Linux
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…
Machine Learning Engineering Open Book
Customizable implementation of the self-instruct paper.
Code for Machine Learning for Algorithmic Trading, 2nd edition.
A project to add scalable state-of-the-art out-of-distribution detection (open set recognition) support by changing two lines of code! Perform efficient inferences (i.e., do not increase inference …
Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
🔥Highlighting the top ML papers every week.
A playbook for systematically maximizing the performance of deep learning models.
Library for automatic retraining and continual learning
Codebase used in the paper "Foundational Models for Continual Learning: An Empirical Study of Latent Replay".
[NeurIPS 2022 Spotlight] Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation
Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
My implementation of PARTS: Unsupervised segmentation with slots, attention and independence maximization
FFCV: Fast Forward Computer Vision (and other ML workloads!)
A complete daily plan for studying to become a Google software engineer.
My personal toolbox for doing datascience (especially deep learning) in python.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image