Parameter-Efficient Model Adaptation
A research team is adapting a very large, pre-trained language model for a specialized task. To save computational resources, they keep all of the model's original multi-billion parameters frozen. Their adaptation method involves creating a small set of 50 new, trainable numerical vectors. For any given input text, the standard numerical vectors representing the text are prepended with these 50 new vectors. The combined sequence is then processed by the frozen model. Only the 50 new vectors are modified during the adaptation process. Explain why this technique is both effective at steering the model for the new task and computationally efficient.
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
Input Composition Formula for Prompt Tuning
An engineer is adapting a large, pre-trained language model for a new task. To do this efficiently, they keep all the original model's parameters frozen. Their adaptation strategy involves modifying the input sequence before it is processed by the model. For any given text, they first convert the text into its standard sequence of numerical token representations. Then, they prepend a separate, short sequence of newly initialized, trainable numerical vectors to the beginning of that sequence. Only these new vectors are updated during training on the new task. Which statement best distinguishes the nature of these prepended, trainable vectors from the standard token representations?
You are examining the input layer of a large language model adapted using a parameter-efficient technique. The input is formed by combining two distinct types of numerical vectors. Match each vector type with its correct description.
Prefix Tuning Architecture
Parameter-Efficient Model Adaptation