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

Fine-tune most popular LLMs for movie sentiment analysis #15

Open
bdzyubak opened this issue Apr 1, 2024 · 1 comment
Open

Fine-tune most popular LLMs for movie sentiment analysis #15

bdzyubak opened this issue Apr 1, 2024 · 1 comment
Assignees
@bdzyubak
Labels
enhancement New feature or request Experiment Run an evaluation and compare multiple approaches in the same data
Milestone
May Release

Comments

@bdzyubak
Copy link
Owner

bdzyubak commented Apr 1, 2024

Fine tune 3 (or more) popular models and compare performance to DistilBERT for the movie sentiment analysis task.

Some choices:
GPT-3
LaMDA
Turing-NLG
XGen
Llama 2 (7 billion)
Gemini

Pick based on suitability for sentiment analysis task, popularity and affordability of tuning.
@bdzyubak bdzyubak added enhancement New feature or request Experiment Run an evaluation and compare multiple approaches in the same data labels Apr 1, 2024
@bdzyubak bdzyubak self-assigned this Apr 1, 2024
@bdzyubak bdzyubak mentioned this issue Apr 1, 2024
Closed
@bdzyubak bdzyubak added this to the May Release milestone Apr 1, 2024
@bdzyubak
Copy link
Owner Author

BERT and its DistilBERT (lean), and ROBERTA (more advanced) - flavors of the same model - have been implemented in the following branch #16. Llama is WIP.

Need to timebox the implementation of the other models - not all are available through transformers, and they may not have an easy interface.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@bdzyubak bdzyubak

Labels
enhancement New feature or request Experiment Run an evaluation and compare multiple approaches in the same data
Projects
Natural Language Processing (LLMs)
Status: No status
Milestone
May Release
Development

No branches or pull requests
1 participant
@bdzyubak