metadata

library_name: transformers
license: mit
language:
  - en
metrics:
  - f1
  - precision
  - recall
base_model:
  - t5-3b
pipeline_tag: text-classification

T5 3b for classifying code comments (multi-label)

This model classifies comments in Python code as 'usage', 'parameters', 'developmentNotes', 'expand' or 'summary'.

Developed by: Fabian C. Peña, Steffen Herbold
Finetuned from: t5-3b
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}
}