As the field of machine learning continues to evolve, organizations are increasingly recognizing the need to develop robust practices for managing their specialized and complex machine learning workflows.
In this talk, the speakers will demonstrate how MLOps practices can be leveraged to deploy large language models in AWS SageMaker. They will showcase the use of popular open-source tools such as the Hugging Face Transformers library and the Deeplake vector database, which can be integrated to build an end-to-end inference pipeline that can be used for various machine learning use cases.
By the end of this demo, attendees will have a better understanding of the key components of an MLOps workflow. This talk promises to be informative for both seasoned machine learning practitioners and beginners, providing valuable insights and cutting-edge techniques. Attendees will discover the power of MLOps in developing and deploying LLMs.