Hugging Face Transformers
Hugging Face Transformers is an open-source machine learning library providing thousands of pretrained models and pipelines for Natural Language Processing, Computer Vision, Audio, and multimodal tasks. This index covers the Transformers library and the surrounding Hugging Face APIs that developers use to run inference, manage models, deploy demos, and serve LLMs at scale.
APIs
Hugging Face Transformers Library
Open-source Python library that provides pretrained models, tokenizers, and pipelines for inference and fine-tuning across NLP, vision, audio, and multimodal tasks. The high-lev...
Hugging Face Inference API
Serverless inference API for running predictions against thousands of models hosted on the Hugging Face Hub. Supports NLP, computer vision, audio, and multimodal tasks through a...
Hugging Face Hub API
REST API for interacting with the Hugging Face Hub - upload, download, and manage models, datasets, and spaces programmatically.
Hugging Face Spaces API
API for deploying and managing machine learning applications and demos using Gradio, Streamlit, or Docker on Hugging Face Spaces.
Text Generation Inference (TGI)
High-performance inference server for large language models with continuous batching, token streaming, tensor parallelism, and OpenAI-compatible chat completions endpoints.