Instructions to use ronan7878/qwen3-4b-medical-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ronan7878/qwen3-4b-medical-finetune with Transformers:

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

pipe = pipeline("text-generation", model="ronan7878/qwen3-4b-medical-finetune")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ronan7878/qwen3-4b-medical-finetune")
model = AutoModelForMultimodalLM.from_pretrained("ronan7878/qwen3-4b-medical-finetune")
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 ronan7878/qwen3-4b-medical-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ronan7878/qwen3-4b-medical-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ronan7878/qwen3-4b-medical-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ronan7878/qwen3-4b-medical-finetune

SGLang

How to use ronan7878/qwen3-4b-medical-finetune 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 "ronan7878/qwen3-4b-medical-finetune" \
    --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": "ronan7878/qwen3-4b-medical-finetune",
		"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 "ronan7878/qwen3-4b-medical-finetune" \
        --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": "ronan7878/qwen3-4b-medical-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ronan7878/qwen3-4b-medical-finetune with Docker Model Runner:
```
docker model run hf.co/ronan7878/qwen3-4b-medical-finetune
```

Qwen3-4B Medical Fine-tune

This is a merged fine-tuned model based on Qwen/Qwen3-4B-Instruct-2507.

Intended Use

The model is designed for medical question-answering experiments with a focus on Traditional Chinese Medicine.

The intended training mix is:

80% Traditional Chinese Medicine data
20% western/general medical reasoning data

Training Data

The training pipeline uses public datasets:

DigitalIntelligenceCenter-of-ICMM/Baize-TCM-Corpus-for-Large-Language-Models-V3
FreedomIntelligence/medical-o1-reasoning-SFT

Please review the original dataset licenses and terms before commercial use.

Limitations

This model is a portfolio and research fine-tune. It is not a medical device and must not be used as a substitute for professional diagnosis or treatment.

It may:

produce incorrect medical advice
confuse Traditional Chinese Medicine and western medical concepts
hallucinate prescriptions, herbs, dosages, contraindications, or diagnoses
miss emergency warning signs

For real-world use, connect it to verified clinical guidelines and require professional review.

Example

User: 最近睡眠不好，舌苔厚腻，容易疲劳，可能是什么情况？
Assistant: 从中医角度看，舌苔厚腻和疲劳可能与湿困脾胃等因素有关，但仅凭这些信息不能诊断。建议结合饮食、二便、脉象和既往病史综合判断，并咨询专业医生。

Downloads last month: 14

Safetensors

Model size

4B params

Tensor type

F16

Model tree for ronan7878/qwen3-4b-medical-finetune

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1741)

this model