1Z0-1127-25 Practice Test 10 — 10 Questions

Question 1

A developer wants to generate text using the OCI Generative AI service via the API. Which endpoint should they use to send a text generation request?

Accepted Answer

/v1/completions. The OCI Generative AI service uses the /v1/completions endpoint for text generation requests, as documented in the OCI Generative AI API reference. This endpoint accepts a prompt and generates a continuation of the text, making it the appropriate choice for general text generation tasks.

Answer

/v1/chat/completions

Answer

/v1/embeddings

Answer

/v1/models

Question 2

A user repeatedly gets the same phrase output by the model. Which parameter adjustment is MOST likely to reduce such repetitive patterns?

Accepted Answer

Increase frequency penalty. Frequency penalty reduces the likelihood of repeating tokens that have already appeared, directly combating repetition.

Answer

Decrease max tokens

Answer

Increase temperature

Answer

Increase top-p

Question 3

What is the primary purpose of an embedding model in a RAG pipeline?

Accepted Answer

To convert text into numerical vectors.. The primary purpose of an embedding model in a RAG pipeline is to convert text into numerical vectors (embeddings) that capture semantic meaning. These vectors enable the retrieval component to efficiently find relevant documents by measuring similarity (e.g., cosine similarity) between the query and stored document embeddings. Without this conversion, the system cannot perform semantic search over unstructured text.

Answer

To generate human-like responses.

Answer

To rank search results.

Answer

To summarize long documents.

Question 4

A data scientist observes that their fine-tuned LLM performs well on training data but generates repetitive and dull responses in production. What is the most likely cause and best solution?

Accepted Answer

The temperature is set too low; increase temperature during inference. The model's repetitive and dull responses indicate that the temperature parameter is too low, causing the model to always select the most probable tokens, leading to deterministic and monotonous outputs. Increasing temperature during inference introduces randomness into token sampling, allowing for more diverse and creative responses. This is a common issue in production LLMs where low temperature settings optimized for training metrics fail to produce engaging real-world outputs.

Answer

The model is overfitted; apply stronger regularization

Answer

The training data lacks diversity; add more varied examples

Answer

The model has too many layers; reduce model size

Question 5

Which TWO OCI Generative AI features are available in the Playground for testing models?

Accepted Answer

Adjusting parameters like temperature and max tokens. The Playground allows interactive testing with parameter adjustment and system prompts. It does not allow fine-tuning or creating dedicated clusters.

Answer

Provisioning a dedicated AI cluster

Answer

Viewing model training metrics

Answer

Submitting a fine-tuning job

Question 6

A security administrator wrote the above IAM policy for a compartment named MyCompartment. Users in the GenerativeAIUsers group can successfully list dedicated AI clusters and models in MyCompartment, but when they try to create an inference endpoint using a model from a different compartment (SharedModels), they get an authorization error. What is the most likely missing policy statement?

Accepted Answer

ALLOW GROUP GenerativeAIUsers TO USE generative-ai-models IN COMPARTMENT SharedModels. The error occurs because the user has permission to list models in MyCompartment but not to use a model from SharedModels when creating an inference endpoint. The missing policy must grant the USE permission on generative-ai-models in the SharedModels compartment, as creating an endpoint requires the ability to reference and use the model resource from that compartment. Option D correctly provides this permission.

Answer

ALLOW GROUP GenerativeAIUsers TO MANAGE generative-ai-models IN COMPARTMENT SharedModels

Answer

ALLOW GROUP GenerativeAIUsers TO USE generative-ai-family IN TENANCY

Answer

ALLOW GROUP GenerativeAIUsers TO USE generative-ai-dedicated-ai-clusters IN COMPARTMENT SharedModels

Question 7

A data scientist is designing a prompt to generate a structured report with sections for Summary, Findings, and Recommendations. Which output format specification in the prompt would be MOST effective?

Accepted Answer

"Provide the output in JSON format with keys: 'summary', 'findings', and 'recommendations'.". Specifying JSON output with clear keys ensures the model returns a structured, machine-parseable result. Natural language descriptions are ambiguous, and markdown may not be reliably parsed.

Answer

"Write a report with three sections: Summary, Findings, Recommendations."

Answer

"Return the report in bullet points."

Answer

"Output the report as a markdown document with headings."

Question 8

Which TWO parameters directly control the randomness and diversity of generated tokens?

Accepted Answer

Temperature. Temperature and top-p (nucleus sampling) are the primary parameters that influence randomness and diversity.

Answer

Stop sequences

Answer

Frequency penalty

Answer

Max tokens

Question 9

A developer is using Cohere Command to answer questions grounded in internal technical manuals. They want to ensure the model only answers based on the provided documents and does not use its pre-trained knowledge. Which Cohere-specific technique should be applied?

Accepted Answer

Use the document-grounded generation syntax by providing documents in the chat history with explicit citation instructions. Cohere's document-grounded generation syntax allows you to supply search results or documents and instruct the model to answer solely from those documents, reducing hallucination.

Answer

Fine-tune the model on the technical manuals

Answer

Set temperature to 0 in the generation parameters

Answer

Use the preamble to instruct the model to answer only from the documents

Question 10

An AI team is fine-tuning a large language model using OCI Data Science and plans to deploy the fine-tuned model using the Generative AI service's custom model deployment. What is the required format for the model artifacts?

Accepted Answer

A .zip archive containing model weights and configuration files. The OCI Generative AI service requires custom model artifacts to be packaged as a .zip archive containing the model weights, configuration files (e.g., config.json, tokenizer files), and any necessary inference code. This format ensures the service can extract and load the model correctly into its managed inference infrastructure, aligning with the standard Hugging Face model repository structure.

Answer

A Git repository URL

Answer

A single .pth file

Answer

A Docker image with the model and inference code