Latent Space: The AI Engineer Podcast cover image

The End of Finetuning — with Jeremy Howard of Fast.ai

Latent Space: The AI Engineer Podcast

00:00

Can you fine-tune new information into a pre-trained model?

You can fine-tune new information into models, as fine-tuning is essentially the same as pre-training. However, we are not good at it because everyone does it differently. Even small models can have impressive capabilities, like generating SQL or coding snippets. There are good models in the 1 to 2 B range, but their performance evaluation is inconsistent. Fine-tuning can be useful for repetitive tasks in an enterprise setting. Smaller models have advantages in terms of resource usage, but their trustworthiness for certain tasks is questionable.

Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner
Get the app