Open Source Models with Hugging Face from Coursera

The availability of models and their weights for anyone to download enables a broader range of developers to innovate and create.

In this course, you’ll select open source models from Hugging Face Hub to perform NLP, audio, image and multimodal tasks using the Hugging Face transformers library. Easily package your code into a user-friendly app that you can run on the cloud using Gradio and Hugging Face Spaces.

You will:

1. Use the transformers library to turn a small language model into a chatbot capable of multi-turn conversations to answer follow-up questions.

2. Translate between languages, summarize documents, and measure the similarity between two pieces of text, which can be used for search and retrieval.

3. Convert audio to text with Automatic Speech Recognition (ASR), and convert text to audio using Text to Speech (TTS).

4. Perform zero-shot audio classification, to classify audio without fine-tuning the model.

5. Generate an audio narration describing an image by combining object detection and text-to-speech models.

6. Identify objects or regions in an image by prompting a zero-shot image segmentation model with points to identify the object that you want to select.

7. Implement visual question answering, image search, image captioning and other multimodal tasks.

8. Share your AI app using Gradio and Hugging Face Spaces to run your applications in a user-friendly interface on the cloud or as an API.

The course will provide you with the building blocks that you can combine into a pipeline to build your AI-enabled applications!

What's inside

Syllabus

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Develops core Natural Language Processing (NLP), audio, image, and multimodal skills

Provides hands-on experience with model deployment and packaging

Utilizes Gradio and Hugging Face Spaces for seamless app sharing and API implementation

Taught by renowned Hugging Face instructors with expertise in NLP, audio, and image processing

May not be suitable for complete beginners in NLP, audio, or image processing

Requires basic knowledge of Python programming

Reviews summary

Practical hugging face for ai applications

According to learners, this course offers a largely positive experience, excelling in providing practical, hands-on skills for leveraging open-source AI models through Hugging Face. Students particularly appreciate the comprehensive coverage of NLP, audio, image, and multimodal tasks. A significant highlight is the focus on deploying AI applications using Gradio and Hugging Face Spaces, noted as a game-changer for prototyping. While praised for clear explanations and relevant content, some learners suggest the pace can be rapid and that a basic understanding of Python and ML concepts is beneficial, as the course prioritizes practical implementation over deep theoretical dives.

Covers diverse AI modalities from NLP to image generation effectively.

"It provides a solid foundation in using Hugging Face for various tasks, from NLP to image generation."

"A very practical course covering a wide range of topics. I particularly enjoyed the multimodal tasks and the deployment aspects."

"The course does a good job of showing the breadth of possibilities. For someone with some ML experience, it's a great way to jump into HF."

Equips learners with practical skills to easily share AI applications.

"The Gradio/Spaces deployment section is a game-changer for sharing projects. I highly recommend it for anyone looking to get started..."

"I loved how they integrated Gradio for creating interactive demos."

"The practical focus and coverage of Gradio/Spaces make it incredibly valuable for quickly prototyping and sharing AI applications!"

Emphasizes building and deploying AI applications through practical exercises.

"The hands-on labs are incredibly helpful, and the Gradio/Spaces deployment section is a game-changer for sharing projects."

"It demystifies using Hugging Face models and shows you how to apply them to real-world problems."

"I was able to build and deploy a multimodal application by the end. The practical focus and coverage of Gradio/Spaces make it incredibly valuable for quickly prototyping..."

Prioritizes practical implementation over deep theoretical details.

"While the examples are good, I often felt I needed more context or deeper explanations. If you're a complete beginner, be prepared to do some extra reading."

"The course is okay, but I wish there was more depth on the 'why' behind certain models or techniques. It's more of a 'how-to' guide."

"My main feedback would be that some explanations felt a bit too high-level for someone without much prior ML exposure."

The course moves quickly, requiring learners to keep up with the material.

"I struggled a bit with the rapid pace. It covers a lot of ground, but sometimes skims over the underlying theory."

"Overall good, but some parts felt a bit rushed. The section on zero-shot classification was very interesting..."

"Some parts are very condensed, so prior ML knowledge is really helpful to keep up."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Open Source Models with Hugging Face with these activities:

Review fundamentals of signal processing for audio applications

Show steps

A strong foundation in signal processing is essential for audio-related tasks. This activity refreshes your knowledge, ensuring a solid understanding.

Browse courses on Signal Processing

Show steps

Read through the Hugging Face documentation on audio processing
Review basic concepts of signal processing, such as sampling, quantization, and filtering

Practice language translation using the transformers library

Show steps

Hands-on practice with the transformers library helps solidify your understanding of language translation techniques.

Show steps

Translate a short paragraph from English to French in Python using the transformers library
Explore different translation models and compare their accuracy

Build an image classification model with Hugging Face Hub

Show steps

This activity provides practical experience in model deployment and serving, enhancing your understanding of the model deployment process.

Show steps

Follow the Hugging Face tutorial on deploying a model to Hugging Face Hub
Deploy your own image classification model to Hugging Face Hub

One other activity

Expand to see all activities and additional details

Show all four activities

Develop a multimodal AI application using Gradio

Show steps

Creating a multimodal AI application allows you to apply your knowledge in a practical project, solidifying your understanding of multimodal AI.

Show steps

Design the user interface for your application using Gradio
Integrate multiple AI models into your application

Career center

Learners who complete Open Source Models with Hugging Face will develop knowledge and skills that may be useful to these careers:

Reading list

We haven't picked any books for this reading list yet.

Open Source Models with Hugging Face

Here's a deal for you

What's inside

Syllabus

Traffic lights

Save this course

Reviews summary

Practical hugging face for ai applications

Activities

Career center

Reading list

Share

Similar courses