Oracle Cloud Infrastructure 2024 Generative AI Professional - 1z0-1127-24 模擬練習

A. It is not optimized for high-dimensional spaces.

B. A vector database stores data in a linear or tabular format.

C. It uses simple row-based data storage.

D. It is based on distances and similarities in a vector space.

A. It penalizes all tokens equally, regardless of how often they have appeared.

B. It applies a penalty only if the token has appeared more than twice.

C. It penalizes only tokens that have never appeared in the text before.

D. It penalizes a token each time it appears after the first occurrence.

A. RAG Token retrieves relevant documents for each part of the response and constructs the answer incrementally.

B. Unlike RAG Sequence, RAG Token generates the entire response at once without considering individual parts.

C. RAG Token does not use document retrieval but generates responses based on pre-existing knowledge only.

D. RAG Token retrieves documents oar/at the beginning of the response generation and uses those for the entire content

A. When the LLM already understands the topics necessary for text generation

B. When the LLM requires access to the latest data for generating outputs

C. When the LLM does not perform well on a task and the data for prompt engineering is too large

D. When you want to optimize the model without any instructions

A. It leads to higher latency in model inference.

B. It limits the number of fine-tuned model deployable on the same GPU cluster.

C. It increases G PU memory requirements for model deployment.

D. It enables the deployment of multiple fine-tuned models.

A. Specifies a string that tells the model to stop generating more content

B. Assigns a penalty to tokens that have already appeared in the preceding text

C. Determines the maximum number of tokens the model can generate per response

D. Controls the randomness of the model's output, affecting its creativity

A. To debug issues in language model outputs

B. To generate test cases for language models

C. To analyze the reasoning process of language

D. To monitor the performance of language models