Ecosystem & Stack: hugging-face

Unsloth Studio provides a unified web interface for efficiently running and training open-source AI models locally across various operating systems and hardware.

An enterprise-ready, model-agnostic SDK for building, orchestrating, and deploying intelligent AI agents and multi-agent systems.

Argilla is a collaboration tool for AI engineers and domain experts to build and maintain high-quality datasets for various AI models, from NLP to LLMs and multimodal systems.

Self-host and serve any open-source LLM as an OpenAI-compatible API endpoint with ease.

An open-source course teaching how to build a production-ready Second Brain AI assistant leveraging LLMs, RAG, agents, and LLMOps for personal knowledge management.

Firefly is an open-source toolkit for efficient large language model training, supporting pre-training, instruction fine-tuning, and DPO with methods like LoRA and QLoRA.

Provides Google Colab notebooks to easily run Stable Diffusion WebUI, including various models and extensions, though it is now outdated and superseded by TostUI.

A PyTorch 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).

vLLM-Omni is an efficient, flexible, and easy-to-use framework extending vLLM to serve omni-modality models (text, image, video, audio) with high throughput and an OpenAI-compatible API.

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.

An open-source implementation of Microsoft's VALL-E X, enabling zero-shot multilingual text-to-speech synthesis and voice cloning with emotion control.

Create dynamic videos by smoothly transitioning between text prompts using Stable Diffusion's latent space exploration.

A pioneering open-source multimodal AI model family designed to serve as a high-performance alternative to commercial models like GPT-4o and GPT-5.