gpt2-large-medical / README.md
Locutusque's picture
Update README.md
0666554
|
raw
history blame
No virus
419 Bytes
metadata
datasets:
  - BI55/MedText
  - pubmed_qa
metrics:
  - bleu
  - perplexity
pipeline_tag: text-generation
widget:
  - text: <|USER|> What is Schizophrenia? <|ASSISTANT|>

A further fine-tuned version of Locutusque/gpt2-large-conversational on MedText and the pqa_labeled subset of pubmed_qa

Evaluation

This model was evaluated using GPT-3.5, and it was asked medical questions. It achieved an average accuracy of 75.8%.