kbressem / medAlpaca

LLM finetuned for medical question answering

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Compare to BioMedLM

rdenaux opened this issue · comments

Congrats on the interesting project and good results! I was wondering if you have considered adding a comparison or finetuning BioMedLM (available from HuggingFace) on your dataset. From their blogpost, they claim a score of 50.3% in MedQA-USMLE. It's not clear how this relates to your benchmark scores, also for USMLE.

commented

Thanks for the suggestion. I'll probably run this comparison, once I am satisfied with the re-implementation of the training.