← back to the directory
Library / SDK Inference & ServingFine-tuning & Training

Transformers

1Pretrained 2models 3for 4text 5and 6beyond

the six Ws · specification

W1 Who

Maintained by Hugging Face.

W2 What

A library providing thousands of pretrained models and a unified API across text, vision, and audio.

W3 Where

A Python library on CPU or GPU with PyTorch, TensorFlow, or JAX backends.

W4 When

Reach for it when you need to load, run, or fine-tune state-of-the-art models.

W5 Why

The de facto standard model library, integrated with the Hugging Face Hub.

W6 With

A deep-learning backend (PyTorch recommended) and model weights from the Hub.

W7 Watch

Built by Hugging Face; open-source (Apache-2.0); runs locally and offline once weights are downloaded.

ModelsNLPInferenceHugging-Face

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.