sradc / SmallPebbleLinks
Small deep learning library written from scratch in Python, using NumPy/CuPy.
☆124Updated 3 years ago
Alternatives and similar repositories for SmallPebble
Users that are interested in SmallPebble are comparing it to the libraries listed below
Sorting:
- An experiment with "freely" wired neural networks (no layers)☆164Updated last year
- Unifying Python/C++/CUDA memory: Python buffered array ↔️ `std::vector` ↔️ CUDA managed memory☆83Updated 2 weeks ago
- A declarative drawing API in Python☆295Updated last year
- Publication-quality data representation library based on Matplotlib.☆167Updated 2 years ago
- A simple transformer implementation without difficult syntax and extra bells and whistles.☆53Updated 2 years ago
- An Implementation of Transformer in Transformer in TensorFlow for image classification, attention inside local patches☆43Updated 3 years ago
- Annotate python source code☆69Updated 5 years ago
- ☆18Updated 3 years ago
- A minimal implementation of autograd (in pure Python) 🍰☆95Updated 4 years ago
- Module 0 - Fundamentals☆107Updated last year
- ☆150Updated 3 years ago
- An implementation of the Nyströmformer, using Nystrom method to approximate standard self attention☆56Updated 3 years ago
- Lightweight Experiment & Resource Monitoring 📺☆189Updated 2 years ago
- ☆40Updated 2 years ago
- convert a scikit-learn decision tree into a Keras model☆39Updated last year
- A deep learning framework created from scratch with Python and NumPy☆238Updated 2 years ago
- A minimal Python kernel so you can run Python in your Python☆39Updated 3 years ago
- Execute a jupyter notebook, fast, without needing jupyter☆132Updated 3 months ago
- Lightweight machine learning library based on OpenCL 1.2☆75Updated 4 years ago
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆253Updated last year
- Lazy, a tool for running things in idle time☆48Updated 4 years ago
- A thin, highly portable toolkit for efficiently compiling dense loop-based computation.☆148Updated 2 years ago
- Python library for embedding large graphs in 2D space, using force-directed layouts.☆163Updated 2 years ago
- Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodes☆241Updated 2 years ago
- A lightweight (serverless) native python parallel processing framework based on simple decorators and call graphs.☆103Updated 3 years ago
- Autograd Engine for Python Written in Python C-API for Speed☆20Updated 2 years ago
- A BERT that you can train on a (gaming) laptop.☆209Updated 2 years ago
- Nod.ai 🦈 version of 👻 . You probably want to start at https://github.com/nod-ai/shark for the product and the upstream IREE repository …☆106Updated 9 months ago
- Documented and Unit Tested educational Deep Learning framework with Autograd from scratch.☆121Updated last year
- Run compute jobs on AWS as if you were running them locally.☆125Updated 3 years ago