aieng-lab/CodeLlama-7b-hf_incivility

CodeLlama 7b for classifying uncivil communications

This model classifies developer interactions (e.g., GitHub issues, mailing lists) as 'civil' or 'uncivil'.

• —Developed by: Fabian C. Peña, Steffen Herbold
• —Finetuned from: meta-llama/CodeLlama-7b-hf
• —Replication kit: https://github.com/aieng-lab/senlp-benchmark
• —Language: English
• —License: Llama 2 Community License Agreement

Citation

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