search

kathrinse / be_great

A novel approach for synthesizing tabular data using pretrained large language models
MIT License
254 stars 43 forks source link

The model for GReaT #8

Closed ZhangTP1996 closed 1 year ago

ZhangTP1996 commented 1 year ago

Thanks for the great work! I am a newbie in NLP so this might be a silly question. I am wondering how to use the GPT-2 model for GReaT? Is it

model = GReaT(llm='gpt2', batch_size=32, epochs=50)

or are there any examples that run GReaT instead of Distill-GReaT?

kathrinse commented 1 year ago

Hey, thanks for your question!

Until now, we only used "distilgpt2" and "gpt2-medium" in our experiments.

But, you should be able to use all the pre-trained models from the HuggingFace Model Hub (https://huggingface.co/models) as large language model (llm) - also "gpt2".