Monitor embedding drift for LLMs deployed from Amazon SageMaker JumpStart
AWS Machine Learning Blog
FEBRUARY 2, 2024
Embeddings capture the information content in bodies of text, allowing natural language processing (NLP) models to work with language in a numeric form. Then we use K-Means to identify a set of cluster centers. A visual representation of the silhouette score can be seen in the following figure.
Let's personalize your content