Classification

Using Small Models for Pre-training or Fine-Tuning

One major approach to improving Large Language Models (LLMs) with smaller models focuses on the training phase, specifically using smaller models during the fine-tuning or pre-training of larger models. Key strategies in this category include using the small model to generate synthetic data for the large model to learn from, using the small model to select and filter appropriate high-quality data from a larger pool, and incorporating an auxiliary loss (such as knowledge distillation loss) based on the small model's outputs into the large model's training objective.

Image 0

0

1

Updated 2026-05-01

Contributors are:

Who are from:

Tags

Foundations of Large Language Models

Ch.4 Alignment - Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences