|
|
|
--- |
|
|
|
|
|
license: apache-2.0 |
|
language: |
|
- zh |
|
widget: |
|
- text: >- |
|
A chat between a curious user and an artificial intelligence assistant. |
|
The assistant gives helpful, detailed, and polite answers to the user's |
|
questions. USER: 你好，請問你可以幫我寫一封推薦信嗎？ ASSISTANT: |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
extra_gated_heading: Acknowledge the license to accept the repository. |
|
extra_gated_prompt: Please contact the author for access. |
|
extra_gated_button_content: Acknowledge license 同意以上內容 |
|
extra_gated_fields: |
|
Name: text |
|
Mail: text |
|
Organization: text |
|
Country: text |
|
Any utilization of the Taiwan LLM repository mandates the explicit acknowledgment and attribution to the original author: checkbox |
|
--- |
|
|
|
 |
|
|
|
# 🌟 Checkout [Taiwan-LLM Demo Chat-UI](http://www.twllm.com) 🌟 |
|
|
|
# Model Card for Taiwan LLM 8x7B-DPO |
|
|
|
Taiwan LLM is an advanced language model tailored for Traditional Chinese, focusing on the linguistic and cultural contexts of Taiwan. |
|
|
|
|
|
## Model description |
|
|
|
- **Model type:** A 8x7B parameter Mixtral MoE model fine-tuned on a mix of publicly available, synthetic datasets. |
|
- **Language(s) (NLP):** Primarily Traditional Chinese (zh-tw) |
|
- **Finetuned from model:** [yentinglin/Taiwan-LLM-MoE-alpha](https://huggingface.co/yentinglin/Taiwan-LLM-MoE-alpha) |
|
|
|
### Model Sources |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** https://github.com/MiuLab/Taiwan-LLaMa |
|
- **Demo:** https://twllm.com/ |
|
|
|
## Performance |
|
|
|
Checkout leaderboard in [Tw Chatbot Arena](https://arena.twllm.com/) |
|
|
|
TMMLUS+ score: |
|
- yentinglin/Taiwan-LLM-MoE-alpha: 43.93 |
|
- yentinglin/Taiwan-LLM-8x7B-DPO: TBD |
|
|
|
## Intended uses |
|
|
|
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers: |
|
|
|
```python |
|
# pip install transformers>=4.34 |
|
# pip install accelerate |
|
|
|
import torch |
|
from transformers import pipeline |
|
|
|
pipe = pipeline("text-generation", model="yentinglin/Taiwan-LLM-8x7B-DPO", torch_dtype=torch.bfloat16, device_map="auto") |
|
|
|
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating |
|
messages = [ |
|
{ |
|
"role": "system", |
|
"content": "你是一個人工智慧助理", |
|
}, |
|
{"role": "user", "content": "東北季風如何影響台灣氣候？"}, |
|
] |
|
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |
|
|
|
## Citation |
|
|
|
If you find Taiwan LLM useful in your work, please cite it with: |
|
|
|
``` |
|
@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} |
|
} |
|
``` |
|
|
|
# Acknowledgement |
|
|
|
Ubitus provides valuable compute resources for the project. |
