Instructions to use WhirlwindAI/Qwen-R1-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WhirlwindAI/Qwen-R1-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="WhirlwindAI/Qwen-R1-0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WhirlwindAI/Qwen-R1-0.5B")
model = AutoModelForCausalLM.from_pretrained("WhirlwindAI/Qwen-R1-0.5B")
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 WhirlwindAI/Qwen-R1-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WhirlwindAI/Qwen-R1-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WhirlwindAI/Qwen-R1-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WhirlwindAI/Qwen-R1-0.5B

SGLang

How to use WhirlwindAI/Qwen-R1-0.5B 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 "WhirlwindAI/Qwen-R1-0.5B" \
    --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": "WhirlwindAI/Qwen-R1-0.5B",
		"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 "WhirlwindAI/Qwen-R1-0.5B" \
        --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": "WhirlwindAI/Qwen-R1-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WhirlwindAI/Qwen-R1-0.5B with Docker Model Runner:
```
docker model run hf.co/WhirlwindAI/Qwen-R1-0.5B
```

💡 The Idea

Good answers come from good thinking.

Qwen-R1-0.5B is a fine-tuned version of Qwen2.5-0.5B-Instruct trained to reason before it answers using explicit <thinking> tags.

Instead of jumping straight to the answer, this model generates its reasoning first — making it more transparent, more reliable, and easier to debug.

🧠 How It Works

Every response is structured as:

User: {question}
Assistant: <thinking>{reasoning}</thinking>
{answer}

The model learns to:

Think – generate step-by-step reasoning
Answer – provide the final response

📊 Training Details

Property	Value
Base Model	Qwen2.5-0.5B-Instruct
Dataset	WhirlwindAI/Soft-CoT-1K
Examples	1,355
Method	QLoRA (4-bit)
Epochs	3
Learning Rate	2e-4
LoRA Rank	16
LoRA Alpha	32

🚀 Quick Start

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "WhirlwindAI/Qwen-R1-0.5B"

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)

prompt = "User: What is 2+2?\nAssistant: <thinking>"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50, do_sample=True, temperature=0.7)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📋 Sample Output

User: What is the capital of France?
Assistant: <thinking>Paris is the capital of France.</thinking>
Paris

📈 Performance

The model was evaluated on 10 out-of-distribution questions:

Category	Performance
Format (thinking tags)	✅ Excellent
General Knowledge	✅ Good
Creative Reasoning	✅ Good
Math/Logic	⚠️ Needs improvement
Physics/Science	⚠️ Needs improvement

🔬 What It Learned

Strength	Weakness
✅ Consistent `<thinking>` format	❌ Sometimes hallucinates facts
✅ Generates reasoning before answering	❌ Struggles with multi-step math
✅ Retains general knowledge	❌ Physics reasoning needs more data

🧪 Test It Yourself

questions = [
    "What is the capital of France?",
    "Explain entropy like I'm 5.",
    "Write a short poem about a robot.",
]

for q in questions:
    prompt = f"User: {q}\nAssistant: <thinking>"
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=80)
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📜 Citation

@model{qwenr1_2026,
  title={Qwen-R1-0.5B},
  author={WhirlwindAI},
  year={2026},
  publisher={Hugging Face}
}

🌪️ WhirlwindAI

Efficient Models • Practical Research • Open AI

Downloads last month: -

Safetensors

Model size

0.5B params

Tensor type

F16

Model tree for WhirlwindAI/Qwen-R1-0.5B

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct