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

Libraries

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

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

pipe = pipeline("text-generation", model="nvidia/OpenCodeReasoning-Nemotron-32B")
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")
model = AutoModelForCausalLM.from_pretrained("nvidia/OpenCodeReasoning-Nemotron-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 Settings

vLLM

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

Use Docker

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

SGLang

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

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

wasiuddina commited on Apr 23, 2025

Commit

ee5be7c

verified ·

1 Parent(s): a8ed6d8

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -10

README.md CHANGED Viewed

@@ -42,17 +42,17 @@ Huggingface [04/25/2025] via https://huggingface.co/nvidia/OpenCode-Nemotron-32B
 ## Input
-**Input Type(s):** Text <br>
-**Input Format(s):** String <br>
-**Input Parameters:** One-Dimensional (1D) <br>
-**Other Properties Related to Input:** Context length up to 32,768 tokens <br>
 ## Output
-**Output Type(s):** Text <br>
-**Output Format:** String <br>
-**Output Parameters:** One-Dimensional (1D) <br>
-**Other Properties Related to Output:** Context length up to 32,768 tokens <br>
 Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. <br>
@@ -93,8 +93,8 @@ We used the datasets listed in the next section to evaluate OpenCodeReasoning-32
 ## Inference
-**Engine:** vLLM <br>
-**Test Hardware** NVIDIA H100-80GB <br>
 ## Ethical Considerations:

 ## Input
+- **Input Type(s):** Text <br>
+- **Input Format(s):** String <br>
+- **Input Parameters:** One-Dimensional (1D) <br>
+- **Other Properties Related to Input:** Context length up to 32,768 tokens <br>
 ## Output
+- **Output Type(s):** Text <br>
+- **Output Format:** String <br>
+- **Output Parameters:** One-Dimensional (1D) <br>
+- **Other Properties Related to Output:** Context length up to 32,768 tokens <br>
 Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. <br>
 ## Inference
+- **Engine:** vLLM <br>
+- **Test Hardware** NVIDIA H100-80GB <br>
 ## Ethical Considerations: