yentinglin's picture
add tmmlus+ score
512a750
---
license: apache-2.0
datasets:
- yentinglin/v1
language:
- zh
tags:
- traditional mandarin
- traditional chinese
- taiwan
- moe
- mixtral
- zh-tw
- zh-hant
pretty_name: twllm-moe
---
# Taiwan LLM Mixtrue of Export - Pilot run
<!-- Provide a quick summary of what the model is/does. -->
![image/png](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F5df9c78eda6d0311fd3d541f%2FAMGN-A-fUsaQg-lF35Pzj.png%3C%2Fspan%3E)%3C!-- HTML_TAG_END -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [Yen-Ting Lin 林彥廷](https://yentingl.com/)
- **Compute Funded by:** [HelperAI](https://helperai.ai/)
- **Model type:** [Mixtral](https://huggingface.co/docs/transformers/model_doc/mixtral)
- **Language(s) (NLP):** Traditional Mandarin (zh-tw)
- **License:** [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0)
- **Finetuned from model:** [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
- **TMMLUS+ score:** 38.09223090909092
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** [Taiwan-LLM](https://github.com/MiuLab/Taiwan-LLM)
- **Paper:** [Taiwan-LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model](https://arxiv.org/pdf/2311.17487.pdf)
- **Demo:** [Taiwan LLM ChatUI](https://twllm.com/)
## Citation
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
```bibtex
@misc{lin2023taiwan,
title={Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model},
author={Yen-Ting Lin and Yun-Nung Chen},
year={2023},
eprint={2311.17487},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```