T5-Small Inference Live Demo

See the blog post: Serve T5-Small on Kubernetes for Machine Learning Inference

This machine learning model runs on my own Kubernetes cluster. It does not use Claude, OpenAI, or any other outside service.

Rate limit: 10 requests per 5 minutes (low K8s resources).

Response

Examples

Translation

translate English to German: The house is wonderful.

Sentiment

sst2 sentence: The movie was absolutely fantastic and I loved every minute of it.

Question Answering

question: What is the capital of France?