Oracle Cloud Infrastructure 2025 Generative AI Professional - 1Z0-1127-25 Exam Practice Test

A. Encoder models take a sequence of words and predict the next word in the sequence, whereas decoder models convert a sequence of words into a numerical representation.

B. Encoder models are used only for numerical calculations, whereas decoder models are used to interpret the calculated numerical values back into text.

C. Encoder models and decoder models both convert sequences of words into vector representations without generating new text.

D. Encoder models convert a sequence of words into a vector representation, and decoder models take this vector representation to generate a sequence of words.

A. "Top p" selects tokens from the "Top k" tokens sorted by probability.

B. "Top p" limits token selection based on the sum of their probabilities.

C. "Top p" determines the maximum number of tokens per response.

D. "Top p" assigns penalties to frequently occurring tokens.

A. The token will be the only one considered in the next generation step.

B. The token is more likely to follow the current token.

C. The token is unrelated to the current token and will not be used.

D. The token is less likely to follow the current token.

A. To generate text based only on the model's internal knowledge without external data

B. To retrieve text from an external source and present it without any modifications

C. To store text in an external database without using it for generation

D. To generate text using extra information obtained from an external data source

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

B. It uses simple row-based data storage.

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

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

A. "Top k" selects the next token based on its position in the list of probable tokens, whereas "Top p" selects based on the cumulative probability of the top tokens.

B. "Top k" and "Top p" both select from the same set of tokens but use different methods to prioritize them based on frequency.

C. "Top k" and "Top p" are identical in their approach to token selection but differ in their application of penalties to tokens.

D. "Top k" considers the sum of probabilities of the top tokens, whereas "Top p" selects from the "Top k" tokens sorted by probability.

A. A given StreamlitChatMessageHistory will NOT be persisted.

B. A given StreamlitChatMessageHistory will not be shared across user sessions.

C. StreamlitChatMessageHistory can be used in any type of LLM application.

D. StreamlitChatMessageHistory will store messages in Streamlit session state at the specified key.

A. Hosts the training data for fine-tuning custom models

B. Serves as a designated point for user requests and model responses

C. Updates the weights of the base model during the fine-tuning process

D. Evaluates the performance metrics of the custom models

A. PEFT does not modify any parameters but uses soft prompting with unlabeled data.

B. PEFT involves only a few or new parameters and uses labeled, task-specific data.

C. PEFT modifies all parameters and uses unlabeled, task-agnostic data.

D. PEFT modifies all parameters and is typically used when no training data exists.