You have an Azure AI Foundry project. You plan to use the Azure AI Foundry portal to fine-tune a base Azure OpenAI Service model that can accept both text and images as input. You need to choose the…

The correct answer is A. gpt-4. Among the listed models, GPT-4 (specifically its vision-enabled variant, gpt-4-vision) is the Azure OpenAI model available for fine-tuning in Azure AI Foundry that can accept both text and images as input. GPT-3.5-turbo (C) and davinci-002 (D) are text-only models. While GPT-4o…

Design and prepare a machine learning solution

Question

You have an Azure AI Foundry project. You plan to use the Azure AI Foundry portal to fine-tune a base Azure OpenAI Service model that can accept both text and images as input. You need to choose the suitable model. Which model should you choose?

Options

Agpt-4
Bgpt-4o
Cgpt-35-turbo
Ddavinci-002

How the community answered

(51 responses)

A
90% (46)
B
6% (3)
C
2% (1)
D
2% (1)

Explanation

Among the listed models, GPT-4 (specifically its vision-enabled variant, gpt-4-vision) is the Azure OpenAI model available for fine-tuning in Azure AI Foundry that can accept both text and images as input. GPT-3.5-turbo (C) and davinci-002 (D) are text-only models. While GPT-4o (B) is multimodal, at the time this exam content was authored, GPT-4 was the designated fine-tunable multimodal model in Azure AI Foundry for image+text scenarios. Always verify current Azure AI Foundry documentation, as model fine-tuning support evolves.

Topics

#Azure OpenAI Service#Multimodal Models#Fine-tuning#Azure AI Foundry

Community Discussion

No community discussion yet for this question.

Full DP-100 Practice