Instructions to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", trust_remote_code=True)
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
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"
# 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-3-Nano-30B-A3B-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

SGLang

How to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 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-3-Nano-30B-A3B-BF16" \
    --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-3-Nano-30B-A3B-BF16",
		"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-3-Nano-30B-A3B-BF16" \
        --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-3-Nano-30B-A3B-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
```

suhara commited on Feb 20

Commit

5a48de7

1 Parent(s): 378df16

Upload modeling_nemotron_h.py (#53)

Browse files

- Upload modeling_nemotron_h.py (d4560445935c0bdae7f00faac5c9bb4c34e6b8dd)

Files changed (1) hide show

modeling_nemotron_h.py +4 -0

modeling_nemotron_h.py CHANGED Viewed

@@ -1219,6 +1219,8 @@ class NemotronHPreTrainedModel(PreTrainedModel):
     def _init_weights(self, module):
         """Initialize the weights."""
         if isinstance(module, NemotronHMamba2Mixer):
             module.A_log._no_weight_decay = True
             module.D._no_weight_decay = True
@@ -1250,6 +1252,8 @@ class NemotronHPreTrainedModel(PreTrainedModel):
             #
             # Reference (Megatron-LM): https://github.com/NVIDIA/Megatron-LM/blob/main/megatron/model/gpt_model.py
             for name, p in module.named_parameters():
                 if name in ["out_proj.weight"]:
                     # Special Scaled Initialization --> There are 2 Layer Norms per Transformer Block
                     # Following Pytorch init, except scale by 1/sqrt(2 * n_layer)

     def _init_weights(self, module):
         """Initialize the weights."""
         if isinstance(module, NemotronHMamba2Mixer):
+            if getattr(module.dt_bias, "_is_hf_initialized", False):
+                return
             module.A_log._no_weight_decay = True
             module.D._no_weight_decay = True
             #
             # Reference (Megatron-LM): https://github.com/NVIDIA/Megatron-LM/blob/main/megatron/model/gpt_model.py
             for name, p in module.named_parameters():
+                if getattr(p, "_is_hf_initialized", False):
+                    continue
                 if name in ["out_proj.weight"]:
                     # Special Scaled Initialization --> There are 2 Layer Norms per Transformer Block
                     # Following Pytorch init, except scale by 1/sqrt(2 * n_layer)