Instructions to use open-r1/OpenR1-Qwen-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-r1/OpenR1-Qwen-7B with Transformers:

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

pipe = pipeline("text-generation", model="open-r1/OpenR1-Qwen-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-r1/OpenR1-Qwen-7B")
model = AutoModelForCausalLM.from_pretrained("open-r1/OpenR1-Qwen-7B")
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

vLLM

How to use open-r1/OpenR1-Qwen-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-r1/OpenR1-Qwen-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "open-r1/OpenR1-Qwen-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/open-r1/OpenR1-Qwen-7B

SGLang

How to use open-r1/OpenR1-Qwen-7B 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 "open-r1/OpenR1-Qwen-7B" \
    --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": "open-r1/OpenR1-Qwen-7B",
		"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 "open-r1/OpenR1-Qwen-7B" \
        --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": "open-r1/OpenR1-Qwen-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-r1/OpenR1-Qwen-7B with Docker Model Runner:
```
docker model run hf.co/open-r1/OpenR1-Qwen-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenR1-Qwen-7B

This is a finetune of Qwen2.5-Math-Instruct on OpenR1-220k-Math (default split).

Check out OpenR1-Distill-7B for an improved model that was trained on open-r1/Mixture-of-Thoughts and replicates the performance of DeepSeek-R1-Distill-Qwen-7B across multiple reasoning domains.

Quick start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "open-r1/OpenR1-Qwen-7B"
device = "cuda" 

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."

messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": prompt}
]

Training

We train the model on the default split of OpenR1-220k-Math for 3 epochs. We use learning rate of 5e-5 and extend the context length from 4k to 32k, by increasing RoPE frequency to 300k. The training follows a linear learning rate schedule with a 10% warmup phase. The table below compares the performance of OpenR1-Qwen-7B to DeepSeek-R1-Distill-Qwen-7B and OpenThinker-7B using lighteval.

You can find the training and evaluation code at: https://github.com/huggingface/open-r1/