A. When the model needs to be adapted to perform well in a different domain it was not originally trained on.

B. When there is a significant amount of labeled, task-specific data available.

C. When the model requires continued pre-training on unlabeled data.

D. When there is a need to add learnable parameters to a Large Language Model (LLM) without task-specific training.

A. It selectively updates only a fraction of weights to reduce the number of parameters.

B. It updates all the weights of the model uniformly.

C. It selectively updates only a fraction of weights to reduce computational load and avoid overfitting.

D. It increases the training time as compared to Vanilla fine-tuning.

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

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

C. It uses simple row-based data storage.

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

A. It converts all sparse vectors to dense vectors.

B. It standardizes vector lengths for meaningful comparison using metrics such as Cosine Similarity.

C. It ensures that all vectors represent keywords only.

D. It significantly reduces the size of the database.

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

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

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

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

A. Both Fine-tuning and PEFT require the model to be trained from scratch on new data, making them equally data and computationally intensive.

B. Fine-tuning and PEFT do not involve model modification; they differ only in the type of data used for training, with Fine-tuning requiring labeled data and PEFT using unlabeled data.

C. PEFT requires replacing the entire model architecture with a new one designed specifically for the new task, making it significantly more data-intensive than Fine-tuning.

D. Fine-tuning requires training the entire model on new data, often leading to substantial computational costs, whereas PEFT involves updating only a small subset of parameters, minimizing computational requirements and data needs.

A. To increase the accuracy of the most likely word in the vocabulary

B. To determine the number of words to generate in a single decoding step

C. To adjust the sharpness of probability distribution over vocabulary when selecting the next word

D. To decide to which part of speech the next word should belong

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

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

C. "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.

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. To compress vector data for minimized storage usage

B. To map vectors to a data structure for faster searching, enabling efficient retrieval

C. To convert vectors into a non-indexed format for easier retrieval

D. To categorize vectors based on their originating data type (text, images, audio)