StarCoder2 3b for classifying API reviews

This model classifies API reviews in developer forums (e.g., Stack Overflow) as 'usability', 'others', 'onlysentiment', 'bug', 'performance', 'community', 'documentation', 'compatibility', 'legal', 'portability' or 'security'.

• Developed by: Fabian C. Peña, Steffen Herbold
• Finetuned from: bigcode/starcoder2-3b
• 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}
}