Scribd
Upload
1K views16 pages

1z0 1127 25

K-shot prompting refers to explicitly providing k examples of the intended task in the prompt to guide the model's output. A dataset for fine-tuning an OCI Generative AI model must contain at least 32 prompt/completion pairs to be accepted. Using small datasets with the Vanilla fine-tuning method may lead to overfitting.

Uploaded by

Valentina Heights
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
1K views16 pages

1z0 1127 25

K-shot prompting refers to explicitly providing k examples of the intended task in the prompt to guide the model's output. A dataset for fine-tuning an OCI Generative AI model must contain at least 32 prompt/completion pairs to be accepted. Using small datasets with the Vanilla fine-tuning method may lead to overfitting.

Uploaded by

Valentina Heights
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 16

What does "k-shot prompting" refer to when using Large Language Models for task-specific

applications?

A) The process of training the model on k different tasks simultaneously to improve its
versatility

B) Providing the exact k words in the prompt to guide the model's response

C) Limiting the model to only k possible outcomes or answers for a given task

D Explicitly providing k examples of the intended task in the prompt to guide the model's output

Answer: D
A data scientist is preparing a custom dataset to fine-tune an OCI Generative Al model.

Which criterion must be ensured for the dataset to be accepted?

A) The dataset must be in a proprietary binary format.

B) The dataset must contain at least 32 prompt/completion pairs.

C) The dataset must be divided into separate files for training and validation.

D) The dataset must have a maximum of 1000 sentences per file.

Answer: B

What issue might arise from using small data sets with the Vanilla fine-tuning method in the OCI
Generative Al service?

A) Overfitting

B) Model Drift

C) Data Leakage

D) Underfitting

Answer: A
Which option is available when moving an endpoint resource to a different compartment in
Generative Al Agents?

A) Modify the endpoint's data source to match the new compartment.

B) Create a duplicate endpoint in the new compartment manually.

C) Select a new compartment for the endpoint and move the resource.

D) Archive the endpoint before moving it to a new compartment.

Answer: C

You might also like