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

Libraries

How to use nvidia/Nemotron-Labs-Diffusion-8B with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nvidia/Nemotron-Labs-Diffusion-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/Nemotron-Labs-Diffusion-8B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nvidia/Nemotron-Labs-Diffusion-8B

SGLang

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

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

YongganFu commited on about 15 hours ago

Commit

190e665

verified ·

1 Parent(s): 36e52f3

Patch modeling_ministral.py: handle both `input_embeds` and `inputs_embeds` kwargs

Browse files

Files changed (1) hide show

modeling_ministral.py +9 -1

modeling_ministral.py CHANGED Viewed

@@ -420,13 +420,21 @@ class Ministral3Model(Ministral3PreTrainedModel):
         if kwargs.get("use_causal_mask", False):
             mask_function = create_causal_mask if self.config.sliding_window is None else create_sliding_window_causal_mask
             causal_mask = mask_function(
                 config=self.config,
-                input_embeds=inputs_embeds,
                 attention_mask=attention_mask,
                 cache_position=cache_position,
                 past_key_values=past_key_values,
                 position_ids=position_ids,
             )
         else:

         if kwargs.get("use_causal_mask", False):
             mask_function = create_causal_mask if self.config.sliding_window is None else create_sliding_window_causal_mask
+            # `create_causal_mask` renamed the embeds kwarg from `input_embeds` (transformers <= 4.x)
+            # to `inputs_embeds` (transformers >= 5.0). Detect which the installed version uses.
+            import inspect
+            mask_input_kw = (
+                "inputs_embeds"
+                if "inputs_embeds" in inspect.signature(mask_function).parameters
+                else "input_embeds"
+            )
             causal_mask = mask_function(
                 config=self.config,
                 attention_mask=attention_mask,
                 cache_position=cache_position,
                 past_key_values=past_key_values,
                 position_ids=position_ids,
+                **{mask_input_kw: inputs_embeds},
             )
         else: