Instructions to use yentinglin/Taiwan-LLM-13B-v2.0-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yentinglin/Taiwan-LLM-13B-v2.0-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="yentinglin/Taiwan-LLM-13B-v2.0-base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yentinglin/Taiwan-LLM-13B-v2.0-base")
model = AutoModelForCausalLM.from_pretrained("yentinglin/Taiwan-LLM-13B-v2.0-base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yentinglin/Taiwan-LLM-13B-v2.0-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yentinglin/Taiwan-LLM-13B-v2.0-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yentinglin/Taiwan-LLM-13B-v2.0-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yentinglin/Taiwan-LLM-13B-v2.0-base

SGLang

How to use yentinglin/Taiwan-LLM-13B-v2.0-base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "yentinglin/Taiwan-LLM-13B-v2.0-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yentinglin/Taiwan-LLM-13B-v2.0-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "yentinglin/Taiwan-LLM-13B-v2.0-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yentinglin/Taiwan-LLM-13B-v2.0-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yentinglin/Taiwan-LLM-13B-v2.0-base with Docker Model Runner:
```
docker model run hf.co/yentinglin/Taiwan-LLM-13B-v2.0-base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🌟 Checkout Taiwan-LLM Demo Chat-UI 🌟

Model Card for Taiwan LLM 13B v2.0 base

Taiwan LLM is an advanced language model tailored for Traditional Chinese, focusing on the linguistic and cultural contexts of Taiwan. Developed from a large base model, it's enriched with diverse Taiwanese textual sources and refined through Supervised Fine-Tuning. This model excels in language understanding and generation, aligning closely with Taiwan's cultural nuances. It demonstrates improved performance on various benchmarks like TC-Eval, showcasing its contextual comprehension and cultural relevance. For detailed insights into Taiwan LLM's development and features, refer to our technical report.

Model description

Model type: A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
Language(s) (NLP): Primarily Traditional Chinese (zh-tw)
Finetuned from model: meta-llama/Llama-2-13b-hf

Model Sources

Repository: https://github.com/MiuLab/Taiwan-LLaMa
Demo: https://twllm.com/

Performance

Intended uses

You should fine-tuned this model for instruction-following / chat application.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 5.0

Citation

If you find Taiwan LLM is 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

Taiwan LLM v2 is conducted in collaboration with Ubitus K.K.. Ubitus provides valuable compute resources for the project.

Disclaimer

This model is provided “as‑is” and without warranties of any kind. Users are solely responsible for evaluating the accuracy and suitability of the outputs. The developers assume no liability for any direct or indirect damages arising from its use.
The model is strictly not intended for high‑risk applications such as medical diagnosis, legal advice, or financial investment. For such use cases, please consult qualified professionals.

本模型「如是」（as‑is）提供，使用者須自行評估結果之正確性與適用性。開發者對於使用本模型所引發之任何直接或間接損失，不承擔任何法律責任。
嚴禁用於醫療診斷、法律諮詢、金融投資等高風險場景；若有相關需求，請尋求專業人員協助。

Downloads last month: 19

Safetensors

Model size

13B params

Tensor type

BF16

Model tree for yentinglin/Taiwan-LLM-13B-v2.0-base

Quantizations

4 models

Paper for yentinglin/Taiwan-LLM-13B-v2.0-base

Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model

Paper • 2311.17487 • Published Nov 29, 2023 • 2