Who it's for
For people who write a little Python and want to find, run and share open models. You need a free Hugging Face account, Python 3.11 or later (the version Transformers is tested from) and a terminal.
Lessons
- 1Hugging Face tutorial: find, check and download open modelsA Hugging Face tutorial for Python users: find a model on the Hub, read its card and license, request a gated model and download it with the hf CLI.
- 2Transformers pipeline: run open models in Python, on CPU or GPUA Transformers pipeline tutorial: install it, classify and generate text, chat with an instruction model, and choose a device and dtype that fit your memory.
- 3Hugging Face Inference API: call hosted open models with Inference ProvidersCall hosted open models through Inference Providers, the successor to the Hugging Face Inference API: a token, InferenceClient, the OpenAI client and curl.
- 4Hugging Face Spaces and Gradio tutorial: build a demo and host itA Gradio tutorial for Hugging Face Spaces: build a demo with gr.Interface, run it locally, then host it on a Space with its requirements, secrets and ZeroGPU.
Frequently asked questions
Do I need a GPU for this Hugging Face course?
No. Lesson 2 runs small models on a CPU, lesson 3 sends the heavy work to hosted providers, and lesson 4 explains the shared ZeroGPU option for demos. A GPU only makes bigger local models practical.
Is the Hugging Face course free?
Yes, the lessons are free to read. Some steps can cost money on Hugging Face itself: calls to hosted models use credits, and most Gradio Spaces need a paid plan, which lessons 3 and 4 explain.
How is this course different from the local AI course?
The local AI course runs models through Ollama and LM Studio, apps that hide the Python. This course works in Python with Hugging Face libraries, so you choose the exact model files, settings and hosting yourself.
What should I learn after this course?
The Fine-tuning course is next. It trains an open model on your own data with LoRA, then runs the result locally and shares it on the Hub. The MCP course follows it.