Oracle Cloud Infrastructure 2025 Generative AI Professional - 1Z0-1127-25 Free Exam Questions

A. Soft Prompting and continuous pretraining are both methods that require no modification to the original parameters of the model.

B. Fine-tuning modifies all parameters using labeled, task-specific data, whereas Parameter Efficient Fine-Tuning updates a few, new parameters also with labeled, task-specific data.

C. Fine-tuning and continuous pretraining both modify all parameters and use labeled, task-specific data.

D. Parameter Efficient Fine-Tuning and Soft Prompting modify all parameters of the model using unlabeled data.

A. It picks the most likely word at each step of decoding.

B. It chooses words randomly from the set of less probable candidates.

C. It selects words based on a flattened distribution over the vocabulary.

D. It requires a large temperature setting to ensure diverse word selection.

A. It sources information from databases to use in text generation.

B. It interacts with the user to understand the query better.

C. It evaluates and prioritizes the information retrieved by the Retriever.

D. It generates the final text based on the user's query.

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

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

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

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

A. The difference between the accuracy of the model at the beginning of training and the accuracy of the deployed model

B. The improvement in accuracy achieved by the model during training on the user-uploaded dataset

C. The level of incorrectness in the model's predictions, with lower values indicating better performance

D. The percentage of incorrect predictions made by the model compared with the total number of predictions in the evaluation

A. Increased model interpretability

B. Enhanced generalization to unseen data

C. Faster training time and lower cost

D. Reduced model complexity

A. The semantic content of data in high-dimensional vectors

B. The color and size of the font in textual data

C. The grammatical structure of sentences in the data

D. The frequency of each word or pixel in the data

A. Temporal relationships; necessary for predicting future linguistic trends

B. Linear relationships; they simplify the modeling process

C. Hierarchical relationships; important for structuring database queries

D. Semantic relationships; crucial for understanding context and generating precise language

A. Because diffusion models can only produce images

B. Because text representation is categorical unlike images

C. Because text is not categorical

D. Because text generation does not require complex models