Ecosystem & Stack: hugging-face

FlagEmbedding (BGE) is a comprehensive toolkit offering state-of-the-art embedding models for efficient search, Retrieval-Augmented Generation (RAG), and various multimodal AI applications.

A framework for easily self-hosting and serving any open-source Large Language Models as OpenAI-compatible API endpoints in the cloud.

Learn to build a personalized AI assistant leveraging your 'Second Brain' knowledge base using advanced LLM, RAG, and agentic techniques with MLOps best practices.

A free, hands-on course to build a production-ready LLM & RAG system, including a personalized AI replica, applying LLMOps best practices.

Provides Google Colab notebooks for easily deploying and running Stable Diffusion WebUI, enabling AI-powered image generation and training without local hardware.

A Python library implementing LoRA (Low-Rank Adaptation) to efficiently fine-tune large language models by significantly reducing trainable parameters and storage requirements.

BELLE is an open-source project dedicated to fostering the development of Chinese conversational large language models, aiming to make LLMs accessible to everyone.

A modular open-source framework for training constrained value-aligned Large Language Models (LLMs) using Safe Reinforcement Learning from Human Feedback (RLHF).

A framework for efficient, fast, and cheap serving of omni-modality (text, image, video, audio) AI models.

A high-performance data engine for AI and multimodal workloads, processing diverse data types at scale with Python and Rust.

A declarative, transactional Python library for building multimodal AI applications with incremental data storage, transformation, indexing, and orchestration.

A local AI API platform for running various AI models (vision, speech, language) on diverse hardware with an OpenAI-compatible API.

Orpheus TTS is a state-of-the-art open-source text-to-speech system built on a Llama-3b backbone, aiming to generate human-sounding, emotionally rich speech with low latency.

A lightweight and optimized Python library for fast offline large language model inference, offering comparable or better performance than vLLM with a more readable codebase.