Instructions to use nvidia/Nemotron-H-8B-Base-8K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-H-8B-Base-8K with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Nemotron-H-8B-Base-8K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Nemotron-H-8B-Base-8K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Nemotron-H-8B-Base-8K"
# 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/Nemotron-H-8B-Base-8K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-H-8B-Base-8K

SGLang

How to use nvidia/Nemotron-H-8B-Base-8K 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/Nemotron-H-8B-Base-8K" \
    --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/Nemotron-H-8B-Base-8K",
		"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/Nemotron-H-8B-Base-8K" \
        --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/Nemotron-H-8B-Base-8K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Nemotron-H-8B-Base-8K with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-H-8B-Base-8K
```

What’s the Pre-training Data Strategy Behind Nemotron-H?

by Zieksy - opened Jun 14, 2025

Discussion

Zieksy

Jun 14, 2025

I understand that the Nemotron-H-56B-Base model was pre-trained on a dataset of 20T tokens, while the Nemotron-H-8B-Base model was trained on 15T tokens. However, the publicly available nemotronCC dataset is 6.3T tokens.

Could anyone provide insights into how this 6.3T dataset is expanded or supplemented to reach the required sizes of 15T and 20T tokens? Are there additional datasets used, or are there specific methods for augmenting the existing nemotronCC dataset?

Looking forward to any information or guidance.

Thank you very much!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment