---
license: cc-by-nc-4.0
datasets:
- passing2961/multifaceted-skill-of-mind
language:
- en
base_model:
- meta-llama/Llama-3.1-8B-Instruct
tags:
- conversational ai
- conversational skill
---

# Thanos-8B Model Card

[🧠 Multifaceted Skill-of-Mind](https://huggingface.co/datasets/passing2961/multifaceted-skill-of-mind) | [🤖 Thanos-1B](https://huggingface.co/passing2961/Thanos-1B) | [🤖 Thanos-3B](https://huggingface.co/passing2961/Thanos-3B) | [💻 Github](https://github.com/passing2961/Thanos) | [📄 Arxiv](https://arxiv.org/abs/2411.04496) | [📕 PDF](https://arxiv.org/pdf/2411.04496)

> 🚨 Disclaimer: All models and dataset are intended to be used for research purposes only.

## Model Description
- **Repository:** [Code](https://github.com/passing2961/Thanos)
- **Paper:** Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model
- **Point of Contact:** [Young-Jun Lee](mailto:yj2961@kaist.ac.kr)

## Model Details
- **Model**: Thanos-series is a fully open-source, skill-of-mind-infused LLM designed to help general conversational agents respond in a more human-like way.
- **Date**: Thanos-series was trained in 2024.
- **Training Dataset**: [100K Multifaceted Skill-of-Mind](https://huggingface.co/datasets/passing2961/multifaceted-skill-of-mind)
- **Architecture**: Thanos-8B was trained on top of [LLaMA-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).

## How to Use

## License and Recommendations

🚨 Thanos-8B 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:

```
@misc{lee2024thanosenhancingconversationalagents,
      title={Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model}, 
      author={Young-Jun Lee and Dokyong Lee and Junyoung Youn and Kyeongjin Oh and Ho-Jin Choi},
      year={2024},
      eprint={2411.04496},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2411.04496}, 
}
```