Instructions to use nvidia/Llama-3_1-Nemotron-51B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Llama-3_1-Nemotron-51B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Llama-3_1-Nemotron-51B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nvidia/Llama-3_1-Nemotron-51B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Llama-3_1-Nemotron-51B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Llama-3_1-Nemotron-51B-Instruct"
# 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/Llama-3_1-Nemotron-51B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Llama-3_1-Nemotron-51B-Instruct

SGLang

How to use nvidia/Llama-3_1-Nemotron-51B-Instruct 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/Llama-3_1-Nemotron-51B-Instruct" \
    --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/Llama-3_1-Nemotron-51B-Instruct",
		"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/Llama-3_1-Nemotron-51B-Instruct" \
        --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/Llama-3_1-Nemotron-51B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Llama-3_1-Nemotron-51B-Instruct with Docker Model Runner:
```
docker model run hf.co/nvidia/Llama-3_1-Nemotron-51B-Instruct
```

itlevy

ishahaf commited on Jul 6, 2025

Commit

f4d9431

verified ·

1 Parent(s): 2e9bdbf

_prepare_generation_config bugfix (failed due to version update in transformers) (#25)

Browse files

- _prepare_generation_config bugfix (failed due to version update in transformers) (aabac526c6963d3107659c16ef56c50408e96b65)

Co-authored-by: Ido Shahaf <ishahaf@users.noreply.huggingface.co>

Files changed (1) hide show

modeling_decilm.py +5 -2

modeling_decilm.py CHANGED Viewed

@@ -833,10 +833,13 @@ class DeciLMPreTrainedModel(PreTrainedModel):
                 module.weight.data[module.padding_idx].zero_()
     def _prepare_generation_config(
-            self, generation_config: Optional[GenerationConfig], **kwargs: dict
     ) -> tuple[GenerationConfig, dict]:
         # DeciLM-specific code
-        generation_config, model_kwargs = super()._prepare_generation_config(generation_config, **kwargs)
         generation_config.cache_implementation = "variable"
         NEED_SETUP_CACHE_CLASSES_MAPPING["variable"] = VariableCache
         return generation_config, model_kwargs

                 module.weight.data[module.padding_idx].zero_()
     def _prepare_generation_config(
+            self,
+            generation_config: Optional[GenerationConfig],
+            *args,
+            **kwargs,
     ) -> tuple[GenerationConfig, dict]:
         # DeciLM-specific code
+        generation_config, model_kwargs = super()._prepare_generation_config(generation_config, *args, **kwargs)
         generation_config.cache_implementation = "variable"
         NEED_SETUP_CACHE_CLASSES_MAPPING["variable"] = VariableCache
         return generation_config, model_kwargs