AI-300 Certification Practice Question #5

Question

You have a deployment of an Azure OpenAI Service base model.
You plan to fine-tune the model.
You need to prepare a file that contains training data for multi-turn chat.
Which file encoding method should you use?

Accepted Answer

The fine-tuning documentation requires training files to be **UTF-8** encoded (with a BOM). UTF-8 covers the full Unicode character set needed for arbitrary multi-turn chat text, while ASCII/ISO-8859-1 are limited single-byte encodings and UTF-16 is not the format the service expects.

More AI-300 practice questions