aieng-lab/codebert-base_requirement-completion

1---2library_name: transformers3license: mit4language:5- en6metrics:7- accuracy8- perplexity9base_model:10- microsoft/codebert-base11pipeline_tag: fill-mask12---13 14# CodeBERT base for filling user actions in requirement specifications15 16This model fills masks ([MASK]) in requirements specifications. During the fine-tuning process, POS verbs were used as a proxy of user actions.17 18- **Developed by:** Fabian C. Peña, Steffen Herbold19- **Finetuned from:** [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base)20- **Replication kit:** [https://github.com/aieng-lab/senlp-benchmark](https://github.com/aieng-lab/senlp-benchmark)21- **Language:** English22- **License:** MIT23 24## Citation25 26```27@misc{pena2025benchmark,28  author    = {Fabian Peña and Steffen Herbold},29  title     = {Evaluating Large Language Models on Non-Code Software Engineering Tasks},30  year      = {2025}31}32```33