Model Card for Model ID

SIGIR-C2I-Dec is a bi-encoder retrieval model specifically fine-tuned for the CodeConvo dataset.

• Paper: Automated Insights Into GitHub Collaboration Dynamics
• Training Dataset: jiebi/CodeConvo

Uses

You can use MTEB to load this model (source code).

To run the IR evaluation task (source code).

Training Details

You can reproduce this with this script (reproduced here for convenience).

Framework versions

• PEFT 0.13.2

Citation

@article{bian2025automated,
  title={Automated Insights Into GitHub Collaboration Dynamics},
  author={Bian, Jie and Arefev, Nikolay and M{\"u}hlh{\"a}user, Max and Welzl, Michael},
  journal={IEEE Access},
  volume={13},
  pages={85526--85542},
  year={2025}
}