Instructions to use MedInjection/QWEN-4B-NAT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MedInjection/QWEN-4B-NAT with Transformers:

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

pipe = pipeline("text-generation", model="MedInjection/QWEN-4B-NAT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MedInjection/QWEN-4B-NAT")
model = AutoModelForCausalLM.from_pretrained("MedInjection/QWEN-4B-NAT")
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 MedInjection/QWEN-4B-NAT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MedInjection/QWEN-4B-NAT

SGLang

How to use MedInjection/QWEN-4B-NAT 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 "MedInjection/QWEN-4B-NAT" \
    --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": "MedInjection/QWEN-4B-NAT",
		"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 "MedInjection/QWEN-4B-NAT" \
        --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": "MedInjection/QWEN-4B-NAT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MedInjection/QWEN-4B-NAT with Docker Model Runner:
```
docker model run hf.co/MedInjection/QWEN-4B-NAT
```

🩺 QWEN-4B-NAT

QWEN-4B-NAT is a fine-tuned version of Qwen-4B-Instruct trained on the MedInjection-FR dataset, a French biomedical instruction corpus combining native, synthetic, and translated medical question–answer pairs.
This model was fine-tuned using Supervised Fine-Tuning (SFT) with DoRA adapters, designed to study how the origin of supervision data influences model adaptation.

🧠 Model overview

Property	Description
Base model	Qwen3-4B-Instruct-2507
Fine-tuning method	DoRA (Weight-Decomposed Low-Rank Adaptation)
Architecture size	~4B parameters
Language	French 🇫🇷
Domain	Biomedical, Clinical, Health
Intended use	Research on instruction tuning and domain adaptation
Caution	Not for clinical or diagnostic use

⚙️ Training setup

Fine-tuning was performed on 30k multiple-choice (MCQ and MCQU) examples for each configuration, using:

10 epochs
Batch size: 12
Learning rate: 1e-4
Gradient accumulation: 8
Cosine scheduler with 5% warmup
LoRA rank: 16, α = 16, dropout = 0.05
Adapters applied to: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

All runs used identical hyperparameters to isolate the effect of data provenance.

📊 Evaluation summary

Evaluation was conducted on French biomedical benchmarks (MCQ, MCQU, OEQ).
Metrics include Exact Match (EM) and Hamming Score for multiple-choice tasks, and BLEU/ROUGE/BERTScore + LLM-as-a-judge for open-ended QA.

See MedInjection-FR GitHub for full results and plots.

📚 Citation

If you use this model, please cite:

Downloads last month: 4

Safetensors

Model size

4B params

Tensor type

F32

Model tree for MedInjection/QWEN-4B-NAT

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1708)

this model

MedInjection
/

QWEN-4B-NAT