TensorFlow is an open source machine learning framework for training models and running ML pipelines.
Open Source: #machine-learning
Catalog projects marked with #machine-learning. Tags work as dedicated landing pages, so related tools are easier to find and connect.
This collection holds 60 projects with a combined 3,668,345 GitHub stars. Main languages: Python, Jupyter Notebook, C++.
About machine learning
Classic machine learning never went away: behind the generative-AI hype still stand gradient boosting, clustering, and battle-tested pipelines. Open source is the industry standard here — almost everything data scientists use daily is open.
The collection mixes libraries, courses, and tools: from teaching materials that walk through algorithms to production frameworks. Stars and community activity are an honest filter, and both are visible right on the cards.
Repositories
Transformers is Hugging Face’s Python library for state-of-the-art models across NLP, vision, audio, and multimodal tasks.
DeepSeek-V3 is DeepSeek’s open model repository with a MoE architecture, 671B total parameters, 37B activated parameters, and materials for running and studying it.
Whisper is OpenAI’s model and Python package for speech recognition, speech translation into English, and language identification in audio files.
PyTorch is an open framework for tensor computation and deep learning in Python, with dynamic neural networks and GPU support.
LLMs from scratch is Sebastian Raschka’s educational repository for implementing a GPT-like language model step by step in PyTorch.
DeepSeek-R1 is DeepSeek’s open reasoning-model series, including R1, R1-Zero, and distilled variants based on Qwen and Llama.
OpenCV is a computer vision library for image processing, video work, and machine perception tasks.
ML For Beginners is Microsoft’s classic machine learning curriculum: 12 weeks, 26 lessons, quizzes, and practical assignments.
vLLM is a high-performance engine for LLM inference and serving with an OpenAI-compatible API, batching, and efficient memory management.
funNLP is a large Chinese catalog of NLP resources: dictionaries, datasets, models, tools, courses, and language-processing projects.
LLM Course is a learning roadmap for large language models covering fundamentals, fine-tuning, quantization, evaluation, notebooks, and engineering scenarios.