Instructions to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-Nano-9B-v2", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-Nano-9B-v2", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-Nano-9B-v2", trust_remote_code=True, device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nvidia/NVIDIA-Nemotron-Nano-9B-v2" # 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/NVIDIA-Nemotron-Nano-9B-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2
- SGLang
How to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 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/NVIDIA-Nemotron-Nano-9B-v2" \ --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/NVIDIA-Nemotron-Nano-9B-v2", "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/NVIDIA-Nemotron-Nano-9B-v2" \ --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/NVIDIA-Nemotron-Nano-9B-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-Nano-9B-v2 with Docker Model Runner:
docker model run hf.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2
Can we have more detailed instructions on installing dependencies?
Hi team,
Can we have more detailed instructions on installing additional python dependencies? It seems that the model requires causal_conv1d and mamba_ssm packages to be installed, but this information is missing in the README file. Also I wasn't able to install causal_conv1d due to my old Ubuntu version of 20.04 that doesn't have new GCC version. It would be great if you can provide more information on how to get the model properly setup with pure conda env and what's the minimum OS requirements, etc.
Thanks,
Steve
There is also a complex dependency expectations to get mamba-ssm packages to work with specific compatibility required between torch and cuda packages. So it would nice to get a requirements file or at least the pinned versions of the most important libraries.