Instructions to use nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat", 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-Labs-Teacher-Chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat"
# 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-Labs-Teacher-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat

SGLang

How to use nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat 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-Labs-Teacher-Chat" \
    --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-Labs-Teacher-Chat",
		"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-Labs-Teacher-Chat" \
        --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-Labs-Teacher-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-Labs-Teacher-Chat
```

dmax123 commited on 8 days ago

Commit

2ceef67

verified ·

1 Parent(s): 58eac55

Add files using upload-large-folder tool

Browse files

Files changed (11) hide show

model-00003-of-00225.safetensors +3 -0
model-00045-of-00225.safetensors +3 -0
model-00056-of-00225.safetensors +3 -0
model-00060-of-00225.safetensors +3 -0
model-00097-of-00225.safetensors +3 -0
model-00098-of-00225.safetensors +3 -0
model-00101-of-00225.safetensors +3 -0
model-00103-of-00225.safetensors +3 -0
model-00187-of-00225.safetensors +3 -0
model-00196-of-00225.safetensors +3 -0
model-00218-of-00225.safetensors +3 -0

+version https://git-lfs.github.com/spec/v1
+oid sha256:41d397ec217b9ac5c0880651ba6405e3b3842c7ebff23b0a36e9749e7c63661d
+size 4991252600

+version https://git-lfs.github.com/spec/v1
+oid sha256:39a8191d7455ec5d82d0fdf460f9df16d12aec787f93ed14934cdee74762f091
+size 4991252840

+version https://git-lfs.github.com/spec/v1
+oid sha256:ffff5ee11a3d38d55c49d3c7ab8c4715afba21f907357c83295b7633ff6cfa83
+size 4987305808

+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d30e1d79911eeb00b6e70574b4aad3df676f17890cd59ba3f658cb81914785
+size 4987305952

+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbd2f5e94b56c584160feca8706fb7f902af3fd35e10a60df6550e276563ab8
+size 4991515400

+version https://git-lfs.github.com/spec/v1
+oid sha256:d482678304cbc12253f83fad82f84bb844cdf20397ad1827e873c8996d449fef
+size 4991252736

+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c526116efc87b5419c1e067aab2d555b65c8e2fd908616d5e21cbc7f75f4c6
+size 4941123984

+version https://git-lfs.github.com/spec/v1
+oid sha256:2012a7f5965bc8d92afb39c3cac147c44116a29eacd8978806ae82ef3fd84538
+size 4991253080

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@