Program profile · official sources
LLM Course
A free, self-paced Hugging Face course for Python programmers who want to use and fine-tune open LLMs.
Commercial status: no commercial relationship is documented for this page. The verification link goes directly to the official provider source.
Who it is for
Python programmers, ideally with an introductory deep learning course behind them, who want to use and fine-tune open models with the Hugging Face libraries.
Who should skip it
Skip it if you need a certificate: the FAQ says there is currently no certification for this course.
Facts checked 28 Oct 2026
- Price
- Free
- (As shown in the United States on 28 October 2026, the course introduction says "It's completely free and without ads." The FAQ says there is currently no certification for this course. Zero applies to course access; compute for running the notebooks on Google Colab or Amazon SageMaker Studio Lab is not priced on the page.)
- Provider link
See the course and enroll at Hugging Face (official site) ↗
Official site. No commission.
- Time
- 12 chapters plus a setup chapter; each chapter is designed to be completed in 1 week at approximately 6-8 hours of work per week (provider estimate); you can take as much time as you need
- Level
- Intermediate (the page requires a good knowledge of Python and suggests an introductory deep learning course first)
- Credential
- Not listed
- Prerequisites
- Requires a good knowledge of Python. The page says it is better taken after an introductory deep learning course, such as fast.ai's Practical Deep Learning for Coders or a DeepLearning.AI program, and does not expect prior PyTorch or TensorFlow knowledge, though some familiarity helps.
- Format
- Free online self-paced course in documentation chapters with videos and code that runs in Google Colab or Amazon SageMaker Studio Lab; questions go to the Hugging Face forums.
Sources ↗
What you actually do
Code for each section runs in Google Colab or Amazon SageMaker Studio Lab, and chapter 1 ends with a quick quiz; the forums hold a list of project ideas for further practice.
Before you start
Requires a good knowledge of Python. The page says it is better taken after an introductory deep learning course, such as fast.ai's Practical Deep Learning for Coders or a DeepLearning.AI program, and does not expect prior PyTorch or TensorFlow knowledge, though some familiarity helps.
Curriculum
The FAQ says each chapter is designed to be completed in 1 week at approximately 6-8 hours of work, and you can take as much time as you need.
| Entry | Subject | Listed time | Share | Role | Observed |
|---|---|---|---|---|---|
| 1 | 0. Setup | Not stated | Not calculated | Setup chapter. | 2026-10-28 |
| 2 | 1. Transformer models | Not stated | Not calculated | NLP and LLMs, what Transformers can do and how they work, inference with LLMs, bias and limitations; quick quiz. | 2026-10-28 |
| 3 | 2. Using 🤗 Transformers | Not stated | Not calculated | Chapters 1 to 4 introduce the main concepts of the Transformers library. | 2026-10-28 |
| 4 | 3. Fine-tuning a pretrained model | Not stated | Not calculated | Fine-tuning a Hub model on a dataset. | 2026-10-28 |
| 5 | 4. Sharing models and tokenizers | Not stated | Not calculated | Sharing results on the Hugging Face Hub. | 2026-10-28 |
| 6 | 5. The 🤗 Datasets library | Not stated | Not calculated | Chapters 5 to 8 cover the Datasets and Tokenizers libraries, classic NLP tasks and LLM techniques. | 2026-10-28 |
| 7 | 6. The 🤗 Tokenizers library | Not stated | Not calculated | The Tokenizers library. | 2026-10-28 |
| 8 | 7. Classical NLP tasks | Not stated | Not calculated | Common language processing tasks. | 2026-10-28 |
| 9 | 8. How to ask for help | Not stated | Not calculated | Getting help. | 2026-10-28 |
| 10 | 9. Building and sharing demos | Not stated | Not calculated | Building and sharing demos of your models on the Hub. | 2026-10-28 |
| 11 | 10. Curate high-quality datasets | Not stated | Not calculated | Advanced LLM topic. | 2026-10-28 |
| 12 | 11. Fine-tune Large Language Models | Not stated | Not calculated | Advanced LLM topic. | 2026-10-28 |
| 13 | 12. Build Reasoning Models | Not stated | Not calculated | Advanced LLM topic; marked new on the page. | 2026-10-28 |
US price
| Purchase information | Recorded terms |
|---|---|
| Access | As shown in the United States on 28 October 2026, the course introduction says "It's completely free and without ads." The FAQ says there is currently no certification for this course. Zero applies to course access; compute for running the notebooks on Google Colab or Amazon SageMaker Studio Lab is not priced on the page. |
| What the zero covers | No fee is stated for the course. No certificate is offered, so there is no credential cost. Costs of third-party notebook environments are not stated on the page. |
Alternatives
Attention in Transformers: Concepts and Code in PyTorch
| Provider and format | Level | Workload | Award | US price observation |
|---|---|---|---|---|
| DeepLearning.AI · Online self-paced learning with video lessons and listed activities | Beginner | 1h16m listed course duration | DeepLearning.AI Accomplishment | Currency not specified 0. As shown in the United States on 16 October 2026, the provider support page allows free content access, excluding certificates and Accomplishments. Zero applies only to content access, not a credential-inclusive total. The course header marks its 1 graded assignment as Pro access. No complete third-party API, software or compute budget is established. The course page describes free access as limited to the platform beta; no end date is stated. No numeric Pro subscription price is established by this course page or the visible membership capture. |
| Entry and assessment questions | Recorded answer |
|---|---|
| Who is it aimed at? | Python learners understanding attention in transformer language models. |
| What preparation is required? | Basic Python knowledge is the stated learner background; the page does not list a separate formal mathematics prerequisite. The course header marks its 1 graded assignment as Pro access. Free content access does not establish access to every listed assessment or project. |
| What remains unconfirmed? | Expiry and renewal are not stated in the sources we checked. |
Official source · 2026-10-16 | Official source · 2026-10-16 | Official source · 2026-10-16
Transformers in Practice
| Provider and format | Level | Workload | Award | US price observation |
|---|---|---|---|---|
| DeepLearning.AI · Online course with video lessons and listed learning activities | Intermediate | 11h1m listed course duration; individual activity estimates are rounded | Course certificate with Pro | As shown in the United States on 15 October 2026, the course FAQ quotes DeepLearning.AI Pro at USD 30 per month billed monthly, or USD 25 per month billed annually. These are recurring membership quotes, not a fixed completion cost; an annual charged total is not separately stated and is not calculated here. Taxes may apply by location. The certificate requires Pro. |
| Entry and assessment questions | Recorded answer |
|---|---|
| Who is it aimed at? | Software engineers, ML engineers and developers working with LLMs. |
| What preparation is required? | Learners should be comfortable using LLMs through an API or chat interface and understand basic neural network concepts such as weights, layers and training. Prior model-building from scratch is not required. |
| What remains unconfirmed? | Expiry and renewal are not stated in the sources we checked. |
Questions before enrolling
Where can I ask a question during the Hugging Face LLM Course?
Per the FAQ: click the "Ask a question" banner at the top of a section to be redirected to the matching section of the Hugging Face forums; a list of project ideas is also on the forums. Observed 28 October 2026.
Change log
- : Initial record from the official programme page captured from the United States on 28 October 2026. · Source