Skip to content
Project categories

Machine Learning · GitHub

Train, evaluate, and run machine learning models.

Useful GitHub projects

12,832 projects
1,859stars+1in 24h
responsible-ai-toolbox preview

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.

model2vec

MinishLab

2,286stars+1in 24h

Fast State-of-the-Art Static Embeddings

  • State-of-the-Art Performance: Model2Vec models outperform any other static embeddings (such as GLoVe and BPEmb) by a large margin, as can be seen in our results.
  • Small: Model2Vec reduces the size of a Sentence Transformer model by a factor of up to 50. Our best model is just ~30 MB on disk, and our smallest model just ~8 MB (making it the smallest model on MTEB!).

laya-mlx

mizorewww

7,114stars+1in 24h
laya-mlx preview

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

Machine LearningPythonApache-2.0GitHub
405stars+1in 24h

Scikit-learn compatible library for molecular fingerprints and chemoinformatics

  • over 30, e.g. ECFP, Avalon, MACCS, Mordred, PubChem
  • all with a uniform .transform() API

modelscope

modelscope

9,224stars+1in 24h
modelscope preview

ModelScope: bring the notion of Model-as-a-Service to life.

  • ModelScope offers a model-centric development and application experience. It streamlines the support for model training, inference, export and deployment, and facilitates users to build their own MLOps based on the ModelScope ecosystem.
  • For the model inference and training process, a modular design is put in place, and a wealth of functional module implementations are provided, which is convenient for users to customize their own model inference, training and other processes.
Machine LearningPythonApache-2.0GitHub

ggmlc

monatis

81stars+1in 24h
ggmlc preview

A multi-framework neural network compiler lowering PyTorch, JAX, Flax, and Keras models to portable, high-performance GGML execution

JointBERT

monologg

752stars+1in 24h
JointBERT preview

Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"

Machine LearningPythonApache-2.0GitHub

stats

montanaflynn

3,031stars+1in 24h

A well tested and comprehensive Golang statistics library package with no dependencies.

Framegen

MONZikWasTaken

223stars+1in 24h
Framegen preview

Real-time neural frame interpolation in the browser: hand-written WGSL runtime on raw WebGPU, 2.9 MB model, 2x-6x any <video> at 3-4 ms per frame. Chrome/Firefox extension.

cadence

muellerberndt

643stars+1in 24h
cadence preview

A brain that learns from live experience. System 1 by default: perception, memory, plasticity and action. Optional System 2 for self-observation and slow corrections.

papertok

mugar123

134stars+1in 24h

Open-source personalized scientific discovery feed powered by arXiv, OpenAlex, PubMed and more.

  • Personalized feed from arXiv, OpenAlex, PubMed, OpenReview, Hugging Face and more.
  • Follow authors, topics, institutions, projects and journals (up to 10, from a journal's page, which its name opens in Read in plain words).
90stars+1in 24h
awesome-medical-imaging-agents preview

Awesome list for medical imaging agents: radiology agents, pathology agents, segmentation agents, medical VLM agents, self-evolving agents, benchmarks, datasets, tools, and papers.