A company uses a foundation model (FM) from Amazon Bedrock for an AI search tool. The company wants to fine-tune the model to be more accurate by using the company's data. Which strategy will successfully fine-tune the model?
A.
Provide labeled data with the prompt field and the completion field.
B.
Prepare the training dataset by creating a .txt file that contains multiple lines in .csv format.
C.
Purchase Provisioned Throughput for Amazon Bedrock.
Provide labeled data with the prompt field and the completion field: Fine-tuning a foundation model (FM) typically involves providing labeled data in the form of prompts (input) and completions (desired output). The model learns from this data to generate more accurate responses tailored to the company’s specific use case. This approach is aligned with how fine-tuning works, where the model adjusts its parameters based on the relationship between inputs (prompts) and outputs (completions).
Fine-tuning a foundation model involves providing labeled training data where each example consists of a prompt (the input to the model) and a completion (the desired output). This structure helps the model learn specific patterns or behaviors tailored to the company’s data and use case.
In Amazon Bedrock, fine-tuning relies on a structured dataset that aligns with the model's learning requirements to improve its accuracy for domain-specific tasks.
Fine-tuning and provisioned throughput are two separate processes in Amazon Bedrock:
Fine-tuning is the process of training the model on specific labeled data to improve its accuracy for particular tasks. This can be done without purchasing provisioned throughput.Provisioned throughput is required after fine-tuning, specifically for using the custom model for inference. It's not needed for the fine-tuning process itself.To test and deploy your model, you need to purchase Provisioned Throughput.
A voting comment increases the vote count for the chosen answer by one.
Upvoting a comment with a selected answer will also increase the vote count towards that answer by one.
So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.
Jessiii
6 days, 20 hours agoap6491
1 month, 3 weeks agoaldricstormcloak
3 months agoDandelion2025
2 months, 2 weeks agoUdyan
3 months, 1 week agojove
3 months, 2 weeks ago