metadata

library_name: transformers
license: mit
language:
  - en
metrics:
  - f1
  - precision
  - recall
base_model:
  - Salesforce/codet5p-770m
pipeline_tag: text-classification

CodeT5+ 770m for classifying code comments (multi-label)

This model classifies comments in Pharo code as 'keyimplementationpoints', 'example', 'responsibilities', 'classreferences', 'intent', 'keymessages' or 'collaborators'.

Developed by: Fabian C. Peña, Steffen Herbold
Finetuned from: Salesforce/codet5p-770m
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}
}