Instructions to use open-r1/OlympicCoder-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-r1/OlympicCoder-32B with Transformers:

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

pipe = pipeline("text-generation", model="open-r1/OlympicCoder-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-r1/OlympicCoder-32B")
model = AutoModelForCausalLM.from_pretrained("open-r1/OlympicCoder-32B")
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/OlympicCoder-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-r1/OlympicCoder-32B"
# 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/OlympicCoder-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/open-r1/OlympicCoder-32B

SGLang

How to use open-r1/OlympicCoder-32B 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/OlympicCoder-32B" \
    --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/OlympicCoder-32B",
		"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/OlympicCoder-32B" \
        --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/OlympicCoder-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-r1/OlympicCoder-32B with Docker Model Runner:
```
docker model run hf.co/open-r1/OlympicCoder-32B
```

lewtun HF Staff commited on Mar 13, 2025

Commit

3d7ab14

verified ·

1 Parent(s): d53a81c

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -13,6 +13,9 @@ pipeline_tag: text-generation
 OlympicCoder-32B is a code mode that achieves very strong performance on competitive coding benchmarks such as LiveCodeBench andthe 2024 International Olympiad in Informatics.
 ## Model description
 - **Model type:** A 32B parameter model fine-tuned on a decontaminated version of the codeforces dataset.
@@ -52,6 +55,9 @@ print(outputs[0]["generated_text"])
 #<think>Okay, I need to write a Python program that calculates the 10th Fibonacci number. Hmm, the Fibonacci sequence starts with 0 and 1. Each subsequent number is the sum of the two preceding ones. So the sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, and so on. ...
 ```
 ## Training procedure
 ### Training hyper-parameters

 OlympicCoder-32B is a code mode that achieves very strong performance on competitive coding benchmarks such as LiveCodeBench andthe 2024 International Olympiad in Informatics.
+* Repository: https://github.com/huggingface/open-r1
+* Blog post: https://huggingface.co/blog/open-r1/update-3
 ## Model description
 - **Model type:** A 32B parameter model fine-tuned on a decontaminated version of the codeforces dataset.
 #<think>Okay, I need to write a Python program that calculates the 10th Fibonacci number. Hmm, the Fibonacci sequence starts with 0 and 1. Each subsequent number is the sum of the two preceding ones. So the sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, and so on. ...
 ```
+> [!IMPORTANT]
+> To ensure that the model consistently outputs a long chain-of-thought, we have edited the chat template to prefill the first assistant turn with a `<think>` token. As a result, the outputs from this model will not show the opening `<think>` token if you use the model's `generate()` method.  To apply reinforcement learning with a format reward, either prepend the `<think>` token to the model's completions or amend the chat template to remove the prefill. Check out our [blog post](https://huggingface.co/blog/open-r1/update-3#lesson-4-prefill-with-think-to-consistently-enable-long-cot) for more details.
 ## Training procedure
 ### Training hyper-parameters