Instructions to use nvidia/OpenCodeReasoning-Nemotron-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/OpenCodeReasoning-Nemotron-7B with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/OpenCodeReasoning-Nemotron-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/OpenCodeReasoning-Nemotron-7B")
model = AutoModelForCausalLM.from_pretrained("nvidia/OpenCodeReasoning-Nemotron-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 nvidia/OpenCodeReasoning-Nemotron-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/OpenCodeReasoning-Nemotron-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": "nvidia/OpenCodeReasoning-Nemotron-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/OpenCodeReasoning-Nemotron-7B

SGLang

How to use nvidia/OpenCodeReasoning-Nemotron-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 "nvidia/OpenCodeReasoning-Nemotron-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": "nvidia/OpenCodeReasoning-Nemotron-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 "nvidia/OpenCodeReasoning-Nemotron-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": "nvidia/OpenCodeReasoning-Nemotron-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/OpenCodeReasoning-Nemotron-7B with Docker Model Runner:
```
docker model run hf.co/nvidia/OpenCodeReasoning-Nemotron-7B
```

wasiuddina commited on Apr 15, 2025

Commit

e1f0cca

verified ·

1 Parent(s): f9f5111

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -14,11 +14,8 @@ tags:
 ## Model Overview
-Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) which is a derivative of [Meta Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct) (AKA the *reference model*). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. The model supports a context length of 128K tokens. This model fits on a single 8xH100 node for inference.
-Llama-3.1-Nemotron-Ultra-253B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. Efficiency (throughput) directly translates to savings. Using a novel Neural Architecture Search (NAS) approach, we greatly reduce the model’s memory footprint, enabling larger workloads, as well as reducing the number of GPUs required to run the model in a data center environment. This NAS approach enables the selection of a desired point in the accuracy-efficiency tradeoff. Furthermore, by using a novel method to vertically compress the model (see details [here](https://arxiv.org/abs/2503.18908)), it also offers a significant improvement in latency.
-The model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Reasoning, Chat, and Tool Calling as well as multiple reinforcement learning (RL) stages using Group Relative Policy Optimization (GRPO) algorithms for reasoning, chat, and instruction-following.
 This model is ready for commercial use.

 ## Model Overview
+OpenCodeReasoning-Distill-Qwen-7B-Instruct is a large language model (LLM) which is a derivative of [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) (AKA the *reference model*).
+It is a reasoning model that is post trained for reasoning while code generation. The model supports a context length of 32K tokens.
 This model is ready for commercial use.