Introducing Lit-GPT: Hackable implementation of open-source large language models released under Apache 2.0 →

Log in or create a free account to track your progress and access additional course materials  

Unit 8: Exercises

Exercise 1: Trying Other LLMs

In Unit 8.7, we finetuned a DistilBERT model and got ~86% accuracy when finetuning only the last layers. In fact, there are many other LLMs that can even get you better performance. For this exercise, experiment with different LLMs for text classification from here.

I’d also be curious to hear about your findings! Finetuning the last layers of a different model, I got 94.9% test accuracy for example. What was your best model? Please feel free to share your results here.

Log in or create a free account to access:

  • Quizzes
  • Completion badges
  • Progress tracking
  • Additional downloadable content
  • Additional AI education resources
  • Notifications when new units are released
  • Free cloud computing credits
Watch Video 1