DP-100 Question #538: Real Exam Question with Answer & Explanation

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?

Options

• AUTF-8
• BUTF-16
• CASCII
• DISO-8859-1

Explanation

Azure OpenAI Service fine-tuning requires training data files to be encoded in a specific format. This question tests knowledge of the required file encoding for multi-turn chat training data.

Common mistakes.

• B. UTF-16 uses 16-bit code units and is not the encoding format accepted by Azure OpenAI fine-tuning; the service specifically requires UTF-8 encoded files.
• C. ASCII only supports 128 characters and lacks support for international and special characters; while it is technically a subset of UTF-8, it is not the specified encoding standard required by Azure OpenAI fine-tuning.
• D. ISO-8859-1 (Latin-1) is a legacy single-byte encoding that does not meet Azure OpenAI Service's fine-tuning file requirements, which mandate UTF-8 encoding.

Concept tested. Azure OpenAI fine-tuning training data file encoding

Reference. https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/fine-tuning

No community discussion yet for this question.