fine-tuning
Table of Contents
Machine learning technique in which you fine-tune a pre-trained model to a specific task.
- pre-trained model
- often time a large model on a large dataset, be quite general.
- fine-tune
- modify some layers(like the final layer for classification) to fit the specific task, and train the model on task’s training data.
Backlinks
foundation model
Foundation model is typically large(parameter numbers) model pre-trained on large(internet-scale) data, and usually fine-tuned in use to downstream(specific) task.