Instructions to use ChenWeiLi/Taiwan-inquiry_7B_v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChenWeiLi/Taiwan-inquiry_7B_v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="ChenWeiLi/Taiwan-inquiry_7B_v1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChenWeiLi/Taiwan-inquiry_7B_v1.0")
model = AutoModelForCausalLM.from_pretrained("ChenWeiLi/Taiwan-inquiry_7B_v1.0", device_map="auto")
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 Settings

vLLM

How to use ChenWeiLi/Taiwan-inquiry_7B_v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChenWeiLi/Taiwan-inquiry_7B_v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChenWeiLi/Taiwan-inquiry_7B_v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ChenWeiLi/Taiwan-inquiry_7B_v1.0

SGLang

How to use ChenWeiLi/Taiwan-inquiry_7B_v1.0 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 "ChenWeiLi/Taiwan-inquiry_7B_v1.0" \
    --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": "ChenWeiLi/Taiwan-inquiry_7B_v1.0",
		"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 "ChenWeiLi/Taiwan-inquiry_7B_v1.0" \
        --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": "ChenWeiLi/Taiwan-inquiry_7B_v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ChenWeiLi/Taiwan-inquiry_7B_v1.0 with Docker Model Runner:
```
docker model run hf.co/ChenWeiLi/Taiwan-inquiry_7B_v1.0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🔎 Taiwan-inquiry_7B_v1.0

"The model was fine-tuned based on the Taiwan-LLM-7B-v2.1-chat model using a dataset that includes 614 authentic dialogues from the National Cheng Kung University Hospital. Additionally, 101 synthetic dialogues were included in the training set. The dialogue content covers topics referenced from OSCE (臨床技能測驗) sample questions in Taiwan. These synthetic dialogues were generated using GPT-3.5 and Gemini-Pro. The training process aimed to enhance the model's performance in understanding and generating responses related to clinical skills assessment scenarios in a medical context."

Model Description

Developed by: Joseph (Chen-Wei) Li, researcher assistant from National Taiwan University Hospital.
Model type: A 7B parameter GPT-like model fine-tuned on a combination of private and synthetic dialogue datasets.
Language(s) (NLP): Traditional Chinese (zh-tw)
Finetuned from model : yentinglin/Taiwan-LLM-7B-v2.1-chat

Usage of the model

The user can take on the role of a doctor, and the model can engage in conversation with you as if it were a patient.
You can provide the model with a brief patient background in the system prompt, and the model will respond based on that prompt.