gauravpgp's picture
Add paper_notes.md, README.md, config.json, training_args.json, model.safetensors, NOTES.md
412de55 verified
|
Raw History Blame Contribute Delete
215 Bytes

Notes

  • check whether the config round-trips through from_pretrained
  • compare parameter counts against a reference implementation
  • move constants into the config file
  • document the expected input shapes