apcl
/

jam_so / README.md
aakashba's picture
Update README.md
f037c66
|
raw
history blame
475 Bytes
metadata
license: bigscience-openrail-m
datasets:
  - apcl/so13m

Jam-so

Jam-so is a GPT2-like model for research in fine-grained Java analysis. It is intended for fine-grained analysis of Java source code at the level of methods, statements, and variables, as a foundation for downstream tasks like code completion, comment generation, and automated bug repair.

Dataset: so13m dataset

Epochs: One

Iterations : ~300,000