Learn Before
A key reason that fine-tuning a model by only training a small set of new vectors prepended to each layer is computationally efficient is that this method inherently requires a much smaller training dataset compared to methods that update the entire model.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Evaluating a Model Adaptation Strategy for a Startup
A research team is adapting a large language model for a specialized task but has a very limited budget for computational resources. They decide to use a method where only a small set of newly introduced, task-specific vectors are trained, while the millions of original model parameters remain unchanged. Which statement best analyzes why this approach is computationally efficient?
A key reason that fine-tuning a model by only training a small set of new vectors prepended to each layer is computationally efficient is that this method inherently requires a much smaller training dataset compared to methods that update the entire model.