Instructions to use nvidia/Nemotron-H-4B-Base-8K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Nemotron-H-4B-Base-8K with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nvidia/Nemotron-H-4B-Base-8K")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/Nemotron-H-4B-Base-8K", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nvidia/Nemotron-H-4B-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-4B-Base-8K" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Nemotron-H-4B-Base-8K", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nvidia/Nemotron-H-4B-Base-8K
- SGLang
How to use nvidia/Nemotron-H-4B-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-4B-Base-8K" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Nemotron-H-4B-Base-8K", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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-4B-Base-8K" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/Nemotron-H-4B-Base-8K", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nvidia/Nemotron-H-4B-Base-8K with Docker Model Runner:
docker model run hf.co/nvidia/Nemotron-H-4B-Base-8K
Update tokenizer_config.json
Browse files- tokenizer_config.json +0 -1
tokenizer_config.json
CHANGED
|
@@ -8005,7 +8005,6 @@
|
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
"bos_token": "<s>",
|
| 8008 |
-
"chat_template": "{{'<SPECIAL_10>System'}}{% for message in messages %}{% if message['role'] == 'system' %}{{'\n' + message['content'].strip()}}{% endif %}{% endfor %}{{'\n'}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n<SPECIAL_11>User\n' + message['content'].strip() + '\n<SPECIAL_11>Assistant\n' }}{% elif message['role'] == 'assistant' %}{{ message['content'].strip() }}{% endif %}{% endfor %}",
|
| 8009 |
"clean_up_tokenization_spaces": false,
|
| 8010 |
"eos_token": "</s>",
|
| 8011 |
"extra_special_tokens": {},
|
|
|
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
"bos_token": "<s>",
|
|
|
|
| 8008 |
"clean_up_tokenization_spaces": false,
|
| 8009 |
"eos_token": "</s>",
|
| 8010 |
"extra_special_tokens": {},
|