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 11, 2025

Commit

9bbd06c

verified ·

1 Parent(s): 83ebd64

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -14

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 license: apache-2.0
 datasets:
-- open-r1/codeforces-cots_decontaminated
 language:
 - en
 base_model:
@@ -10,7 +10,8 @@ pipeline_tag: text-generation
 ---
 # Model Card for OlympicCoder-32B
-OlympicCoder-32B is a medium sized code model, that achieves strong performance on coding benchmarks such as Live Code Bench and the new International Olympiad in Informatics benchmark.
 ## Model description
@@ -19,18 +20,9 @@ OlympicCoder-32B is a medium sized code model, that achieves strong performance
 - **License:** apache-2.0
 - **Finetuned from model:** [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct)
-## Performance
-| Model | LCB | IOI |
-|-------|-----|---------------|
-|GPT-4o|	28.43	|-
-|Claude 3.7 Sonnet	|39.18|	93|
-|QwQ-32B	|60.98	|	127|
-|DeepSeek-R1-Distill-Qwen-32B|	56.58| -|
-|DeepSeek-R1-Distill-Qwen-7B	|37.36|- |
-|Qwen2.5-Coder-32B-Instruct|	28.31|	35|
-|Qwen2.5-Coder-7B-Instruct	|15.83	|	45|
-|DeepSeek-R1	|-|		|137|
-|OlympicCoder-7B	|36.4	|	129|

 ---
 license: apache-2.0
 datasets:
+- open-r1/codeforces-cots
 language:
 - en
 base_model:
 ---
 # Model Card for OlympicCoder-32B
+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
 - **License:** apache-2.0
 - **Finetuned from model:** [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct)
+## Evaluation
+![](./ioi-evals.png)