Currently, I am working through a course on DeepLearning.AI titled Open-Source Models with Hugging Face. The course provides an excellent opportunity to explore the availability of open source models provided by various smaller and bigger companies like facebook, openai, mistral or microsoft.

In this particula course, participants select open-source models from the Hugging Face Hub to perform various tasks, including NLP, audio, image, and multimodal tasks, using the Hugging Face transformers library. It also teaches how to package code into a user-friendly app that can be run on the cloud using Gradio and Hugging Face Spaces.

Although the course is designed to be completed in about an hour, it is taking me a bit longer as I am translating the code from the Jupyter Notebooks into Python code. This translation process is a valuable learning experience, and I am continuously updating the repository on GitHub with my learning progress. The code is published under the MIT License and can be accessed and contributed to by others.

I am pleasantly surprised by the Hugging Face platform and the potential it offers for integrating AI models into custom code. The possibilities for developing new AI-based applications are truly exciting.

Stay tuned for more updates as I continue to delve deeper into this course and share my progress.

Links:
https://github.com/floriankuhlmann/Open-Source-Models-with-Hugging-Face
https://learn.deeplearning.ai/courses/open-source-models-hugging-face/
https://huggingface.co/