-
Penn State University
- https://birkhoffg.github.io
- @BirkhoffGuo
Highlights
- Pro
Block or Report
Block or report BirkhoffG
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
GPT4 based personalized ArXiv paper assistant bot
Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023
Open weights LLM from Google DeepMind.
Modeling, training, eval, and inference code for OLMo
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
Machine Learning Engineering Open Book
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
A multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.
Collection of Summer 2025 tech internships!
Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
Evaluation pipeline for the BabyLM Challenge 2023.
Zero-copy MPI communication of JAX arrays, for turbo-charged HPC applications in Python ⚡
Welcome to the Awesome Feature Learning in Deep Learning Thoery Reading Group! This repository serves as a collaborative platform for scholars, enthusiasts, and anyone interested in delving into th…
An award searching project aims to using public data by airlines more efficiently.
Add a tqdm progress bar to your JAX scans and loops.
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
Extension to nbdev for generating docs with Material for Mkdocs
Train fastai models faster (and other useful tools)
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Hardware accelerated, batchable and differentiable optimizers in JAX.
A playbook for systematically maximizing the performance of deep learning models.
FFCV: Fast Forward Computer Vision (and other ML workloads!)
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/