Starred repositories
All the open source AI Agents hosted on the oTTomator Live Agent Studio platform!
Continuous Thought Machines, because thought takes time and reasoning is a process.
[ICLR 2025] Automated Design of Agentic Systems
Understanding Deep Learning - Simon J.D. Prince
A repository of Python automation scripts that I find usefull
The official code repository for the second edition of the O'Reilly book Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play.
Code and documentation to train Stanford's Alpaca models, and generate the data.
A collection of libraries to optimise AI model performances
Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation
Efficient Transformers for research, PyTorch and Tensorflow using Locality Sensitive Hashing
SwiftRNG Software Kit for Linux, FreeBSD, macOS, and Windows
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.
Probabilistic reasoning and statistical analysis in TensorFlow
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
World Models Experiments
Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).
Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization
Stochastic Adversarial Video Prediction
Activity Recognition Algorithms for the Charades Dataset
Convolutional neural network model for video classification trained on the Kinetics dataset.
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
A simple, extensible Markov chain generator.
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
Code and model for the paper "Improving Language Understanding by Generative Pre-Training"
Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"