English: In this video, we'll be discussing the seamless migration of your applications from OpenAI models to Hugging Face's open-source alternatives. We'll cover the step-by-step process of deploying a Llama3 8B model on a Google Cloud Inference Endpoint and invoking it with the OpenAI client library. Additionally, we'll deploy a Zephyr 7B model on Amazon SageMaker and demonstrate how easily it can be integrated with the OpenAI Messages API. By the end of this video, you'll be equipped with the knowledge to unlock the full potential of open-source models, all without rewriting your existing code!

This video is perfect for data scientists, machine learning engineers, and developers looking to explore the benefits of open-source models and expand their ML engineering toolkit.

1. OpenAI #HuggingFace #MLEngineering

⭐️⭐️⭐️ Don't forget to subscribe to be notified of future videos. Follow me on Medium at https://julsimon.medium.com or Substack at https://julsimon.substack.com. ⭐️⭐️⭐️

Notebooks

• https://gitlab.com/juliensimon/huggingface-demos/-/blob/main/inference-endpoints/llama3-8b-openai.ipynb
• https://gitlab.com/juliensimon/huggingface-demos/-/blob/main/sagemaker-openai/deploy_zephyr_openai.ipynb

Blog: https://huggingface.co/blog/tgi-messages-api