Online Access Free NCP-AI Practice Test

An NAI administrator has successfully imported a model from Hugging Face and created an endpoint for the model. The endpoint is in the Active state. From within the Endpoint section in NAI, the endpoint has been tested with a Sample Request, the response is accurate, and the Status shows SucceedeD.
The administrator has provided the endpoint URL and generated and provided API keys to the developers. However, the developers are having issues connecting to the endpoint. They keep getting 400 Bad Request errors when attempting to prompt the model.
What should the administrator do next to ensure the developers are able to successfully prompt the model?

• A.Provide the developers the 'Sample Request' code from the endpoint by clicking 'View Sample Request'.
• B.Add additional resources to 'scale up' the number of instances of the endpoint.
• C.Re-import the model from Hugging Face, create a new endpoint and provide new URL and API keys to the developers.
• D.Check the Status of the endpoint again to make sure it was not accidentally HibernateD.

An administrator has been asked to verify why the URL NAI dashboard is inaccessible.
Which service could be impacted?

• A.prometheus
• B.kserve
• C.istio
• D.metallb

Immediately after installing NAI, an administrator must verify that every pod in the namespace nai-system is in a ready state using the command kubectl get pods -n nai-system.
Which ready value would indicate a pod is highly available and healthy?

• A.2/2
• B.2/1
• C.1/1
• D.1/2

An administrator has been ask to troubleshoot the import of a new NIM LLM in NAI. The import Status is Pending.
What could be the most common issue?

• A.System is downloading the LLM.
• B.Unauthorized Hugging Face token.
• C.Required storage space is not available.
• D.LLM repository read access restriction.

Refer to the exhibit

An administrator needs to troubleshoot an import failure from a AI/ML user and does not have the admin right to try to do a manual upload of LLM.
What is the cause of the import failure?

• A.Model Instance name test already exists.
• B.AI/ML User does not have the proper rights.
• C.Wrong pre-validated model has been selecteD.
• D.Storage location configuration is not correct.