CodeBERT base for classifying commit messages

This model classifies commit messages in code repositories (e.g., GitHub) as 'perfective', 'corrective' or 'other'.

• Developed by: Fabian C. Peña, Steffen Herbold
• Finetuned from: microsoft/codebert-base
• Replication kit: https://github.com/aieng-lab/senlp-benchmark
• Language: English
• License: MIT

Citation

@misc{pena2025benchmark,
  author    = {Fabian Peña and Steffen Herbold},
  title     = {Evaluating Large Language Models on Non-Code Software Engineering Tasks},
  year      = {2025}
}