Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

High level project description #8

Closed
kjappelbaum opened this issue Jul 10, 2023 · 0 comments
Closed

High level project description #8

kjappelbaum opened this issue Jul 10, 2023 · 0 comments

Comments

@kjappelbaum
Copy link
Contributor

kjappelbaum commented Jul 10, 2023 •
edited
Loading

Tool

  • Create a robust, canonical, implementation of our GPTChem package that also also to use parameter efficient fine-tuning on consumer hardware
  • Allow for easy sharing of models, e.g., via HuggingFaceHub

Scientific questions

  • What happens for different model sizes?
    • For this, Pythia is probably great
  • What happens for different fine-tuning settings?
  • How do the embeddings look like?
  • How reliable are the uncertainty estimates?
    • logprobs
    • ensemble
    • ensemble over different representations
    • conformal prediction
  • Does prompt template augmentation help?
  • Sensitivity to prompt structure
@kjappelbaum kjappelbaum pinned this issue Jul 10, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@kjappelbaum