Instructions to use nvidia/OpenCodeReasoning-Nemotron-32B-IOI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/OpenCodeReasoning-Nemotron-32B-IOI with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/OpenCodeReasoning-Nemotron-32B-IOI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/OpenCodeReasoning-Nemotron-32B-IOI")
model = AutoModelForCausalLM.from_pretrained("nvidia/OpenCodeReasoning-Nemotron-32B-IOI")
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 Settings

vLLM

How to use nvidia/OpenCodeReasoning-Nemotron-32B-IOI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/OpenCodeReasoning-Nemotron-32B-IOI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/OpenCodeReasoning-Nemotron-32B-IOI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/OpenCodeReasoning-Nemotron-32B-IOI

SGLang

How to use nvidia/OpenCodeReasoning-Nemotron-32B-IOI 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 "nvidia/OpenCodeReasoning-Nemotron-32B-IOI" \
    --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": "nvidia/OpenCodeReasoning-Nemotron-32B-IOI",
		"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 "nvidia/OpenCodeReasoning-Nemotron-32B-IOI" \
        --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": "nvidia/OpenCodeReasoning-Nemotron-32B-IOI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/OpenCodeReasoning-Nemotron-32B-IOI with Docker Model Runner:
```
docker model run hf.co/nvidia/OpenCodeReasoning-Nemotron-32B-IOI
```

wasiuddina commited on May 7, 2025

Commit

cf1950e

verified ·

1 Parent(s): 121fec8

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -7

README.md CHANGED Viewed

@@ -1,13 +1,16 @@
 ---
 library_name: transformers
-license: other
-license_name: nvidia-internal-scientific-research-and-development-model-license
-license_link: >-
-  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/
-pipeline_tag: text-generation
 tags:
-  - nvidia
-  - pytorch
 ---
 # OpenCodeReasoning-CPP-Nemotron-32B Overview

 ---
+base_model:
+- Qwen/Qwen2.5-32B-Instruct
+datasets:
+- nvidia/OpenCodeReasoning
+language:
+- en
 library_name: transformers
+license: cc-by-4.0
 tags:
+- nvidia
+- code
+pipeline_tag: text-generation
 ---
 # OpenCodeReasoning-CPP-Nemotron-32B Overview