machine-learning

顺便一提，我们支持 RWKV | 「Intel 2025 人工智能创新大赛」🚀AutoOPS: Provide the chaos brought by language models to the operation and maintenance industry! 🏆使用 LLM 提供的动力实现全自动运维，支持 Windows Server/Linux/macOS/Cisco IOS，可进行全网自动管理，让我们颠覆运维行业【带外管理/自动运维/IoT设备管理/WebHook监控/任意平台/全模态Workflow】

Serve scikit-learn, XGBoost, TensorFlow, and PyTorch models with AWS Lambda container images support.

PyTorch library for Active Fine-Tuning

OasisDB: A minimal and lightweight vector database

EN to JP and JP to EN with transformer models

A free, self-paced 24-week AI engineering course: Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure and Vertex and Bedrock, and Databricks. 43 runnable notebooks, one continuous case study. MIT licensed, no signup. By Zorost Intelligence AI Lab.

A minimal TensorFlow.js re-implementation of Karpathy's minGPT (Generative Pre-trained Transformer). The GPT model itself is <300 lines of code.

Democratization of "PaLI: A Jointly-Scaled Multilingual Language-Image Model"

One place to find variety of resources and a community of contributors, ML Guide is the perfect place to learn, build, and collaborate. Let's dive into the exciting world of machine learning together!

Access to Sulie foundation models for time-series forecasting 📈

⚡ Create handwritten documents from text with a Neural Network!

Absolutely amazing SOTA Google Colab (Jupyter) Notebooks for creating/training SOTA Music AI models and for generating music with Transformer technology (Google XLNet/Transformer-XL)

🌟PolyGPT: An Overview of Agent-Based System Architecture for Autonomous Business Operations

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

openai/whisper + extra features

Implementation of Perceiver, General Perception with Iterative Attention

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

Secure, locally-run Retrieval-Augmented Generation system for document-based question-answering, utilizing Llama 3, Mistral, and Gemini models with a user-friendly Streamlit interface.

Blazing fast training of 🤗 Transformers on Graphcore IPUs

Official implementation of "Tiled Diffusion" [CVPR 2025]