I'm working on a text summarization logic using Google's t5-small model. My implementation relies on the torch and transformers libraries. However, the problem is that when I build the Docker image, it becomes around 13 GB, which exceeds the deployment size limit. Can anyone suggest the best approach to reduce the image size while still supporting the model and required libraries?
New contributor
Sarvesh is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
-
Did you check the image? Maybe it contains some unnecessary files like caches, etc. that are safe to remove?– Naveed AhmedCommented 10 hours ago
Add a comment
|