gpt2-810M-PubMedAbs / README.md
SudharsanSundar's picture
Create README.md
3e21791 verified
metadata
{}

Model Details

  • Architecture: Basic/default GPT-2, decoder only
  • Num params: ~810M
  • Num tokens seen: ~2 B
  • Dataset: PubMed Abstracts subset of The Pile