Question 1

How do pre-trained models used for text embedding in OCI Generative AI represent textual data?

Options :

A : By assigning a unique numerical identifier to each individual word.

B : By converting text into an image format suitable for computer vision tasks.

C : By creating a high-dimensional vector capturing the semantic meaning of the text.

D : By identifying and extracting named entities like people, locations,

Answer: C

Question 2

Most relevant metric When evaluating the performance of semantic search in an LLM application built with OCI Generative AI?

Options :

A : The average time taken to retrieve documents from the vector database.

B : The number of documents retrieved for a given user query.

C : The accuracy of retrieved documents in addressing the user-s intent.

D : The similarity score between the query vector and the retrieved document vectors.

Answer: C

Question 3

: During LLM fine-tuning, what part of the model typically undergoes the most significant adjustments?

Options :

A : The input layer responsible for processing raw text data.

B : The final layers responsible for generating the desired output.

C : All layers of the LLM architecture are adjusted equally.

D : Only the pre-trained word embeddings are updated.

Answer: B

Question 4

Given the following code: Prompt Template (input_variable[‘’rhuman_input",'city’’], template-template) Which statement is true about Promt Template in relation to input_variables?

Options :

A : PromptTemplate requires a minimum of two variables to function property.

B : PromptTemplate can support only a single variable M a time.

C : PromptTemplate supports Any number of variable*, including the possibility of having none.

D : PromptTemplate is unable to use any variables.

Answer: C

Question 5

How does the temperature setting in a decoding algorithm influence the probability distribution over the vocabulary?

Options :

A : Increasing the temperature flattens the distribution, allowing for more varied word choices.

B : Increasing the temperature removes the impact of the most likely word.

C : Temperature has no effect on probability distribution; it only changes the speed of decoding.

D : Decreasing the temperature broadens the distribution, making less likely words more probable.

Answer: A

Free 1Z0-1127-25 Mock Exam – Practice Online Confidently

Buying Options: