CustomGPT / README.md
Arjun-G-Ravi's picture
Update README.md
99e9892 verified
metadata
license: mit

This is a custom model with 123.5M parameter.

  • A modified version of GPT-2
  • More data will be added soon
  • Pretraining was done on Fineweb Edu dataset
  • Finetuning not done