metadata

license: cc-by-nc-4.0
datasets:
  - passing2961/stark-summary
language:
  - en
base_model:
  - meta-llama/Llama-3.2-3B-Instruct
tags:
  - conversational ai
  - conversation summarization

Ultron-Summarizer-3B Model Card

🏠 Homepage | 💻 Github | 📄 Arxiv | 📕 PDF

List of Provided Model Series

Ultron-Summarizer-Series: 🤖 Ultron-Summarizer-1B | 🤖 Ultron-Summarizer-3B | 🤖 Ultron-Summarizer-8B
Ultron 7B: 🤖 Ultron-7B

🚨 Disclaimer: All models and datasets are intended for research purposes only.

Model Description

Repository: Code
Paper: Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge
Point of Contact: Young-Jun Lee

Model Details

Model: Ultron-Summarizer-3B is a fully open-source conversational summarizer that generates summaries for long-term conversations, including those with image-sharing turns.
Date: Ultron-Summarizer-3B was trained in 2024.
Training Dataset: Stark-Summary
Architecture: Ultron-Summarizer-3B was trained on top of LLaMA-3.2-3B.

How to Use

License and Recommendations

🚨 Ultron-Summarizer-3B is intended to be used for research purposes only.

Acknowledgement

This work was supported by a grant of the KAIST-KT joint research project through AI Tech Lab, Institute of convergence Technology, funded by KT [Project No. G01230605, Development of Task-oriented Persona-based Dialogue Generation Combining Multi-modal Interaction and Knowledge Modeling].

Citation

If you find the resources in this repository useful, please cite our work:

@article{lee2024stark,
  title={Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge},
  author={Lee, Young-Jun and Lee, Dokyong and Youn, Junyoung and Oh, Kyeongjin and Ko, Byungsoo and Hyeon, Jonghwan and Choi, Ho-Jin},
  journal={arXiv preprint arXiv:2407.03958},
  year={2024}
}