Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Implementation of the Deep Q-learning algorithm to solve MDPs

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Accurate Neural Network Potential on PyTorch

Joining the modern data stack with the modern ML stack

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit

A curated list of resources for Learning with Noisy Labels

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Quantum Machine Learning

Run PyTorch models in the browser using ONNX.js

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

A repository of concepts related to neural networks for NLP

Automated Time Series Forecasting

A curated list of resources dedicated to Feature Engineering Techniques for Machine Learning

Princeton NLP's pre-training library based on fairseq with DeepSpeed kernel integration 🚃

Hidden Markov Models in Python, with scikit-learn like API

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

Supercharge Your Model Training

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

TorchKGE: Knowledge Graph embedding in Python and PyTorch.

Omnivore: A Single Model for Many Visual Modalities

Books with Jupyter notebooks

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

Pretrained language model with 100B parameters

🚤 Label data at scale. Fun and precision included.

Compare neural networks by their feature similarity

Using modified BiSeNet for face parsing in PyTorch

YOLOv6: a single-stage object detection framework dedicated to industrial applications.