Instructions to use DedeProGames/medqwen-0.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DedeProGames/medqwen-0.5b with Transformers:

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

pipe = pipeline("text-generation", model="DedeProGames/medqwen-0.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DedeProGames/medqwen-0.5b")
model = AutoModelForCausalLM.from_pretrained("DedeProGames/medqwen-0.5b", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DedeProGames/medqwen-0.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DedeProGames/medqwen-0.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/medqwen-0.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DedeProGames/medqwen-0.5b

SGLang

How to use DedeProGames/medqwen-0.5b 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 "DedeProGames/medqwen-0.5b" \
    --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": "DedeProGames/medqwen-0.5b",
		"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 "DedeProGames/medqwen-0.5b" \
        --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": "DedeProGames/medqwen-0.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DedeProGames/medqwen-0.5b with Docker Model Runner:
```
docker model run hf.co/DedeProGames/medqwen-0.5b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Experimental model. This model is intended for research and testing only and must not be used for real medical diagnosis, treatment, or clinical decision-making.

medqwen is a small experimental medical reasoning model based on Qwen2.5-0.5B.
It was trained on DedeProGames/Medical-Reasoning-SFT-Nano.

medqwen is designed to explore medical-style reasoning, question answering, and instruction following in a compact model size. It is focused on being lightweight, simple, and useful for experimentation.

Details

Model name: medqwen
Base model: Qwen2.5-0.5B
Training dataset: DedeProGames/Medical-Reasoning-SFT-Nano
Type: Experimental medical reasoning model

Notes

This model may generate inaccurate, incomplete, or unsafe medical information.
Always verify outputs with trusted medical sources and qualified professionals.