Instructions to use nvidia/Nemotron-Labs-Diffusion-3B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-Labs-Diffusion-3B-Base with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Nemotron-Labs-Diffusion-3B-Base", 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-3B-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/Nemotron-Labs-Diffusion-3B-Base 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-3B-Base"
# 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-3B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-Labs-Diffusion-3B-Base

SGLang

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

Docker Model Runner
How to use nvidia/Nemotron-Labs-Diffusion-3B-Base with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-Labs-Diffusion-3B-Base
```

Nemotron-Labs-Diffusion-3B-Base / config.json

YongganFu

Initial release of Nemotron-Labs-Diffusion-3B-Base

91a60ad about 18 hours ago

raw

history blame contribute delete

1.32 kB

	{
	"ar_loss_weight": 1.0,
	"architectures": [
	"NemotronLabsDiffusionModel"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_implementation": "sdpa",
	"auto_map": {
	"AutoConfig": "configuration_nemotron_labs_diffusion.NemotronLabsDiffusionConfig",
	"AutoModel": "modeling_nemotron_labs_diffusion.NemotronLabsDiffusionModel"
	},
	"block_size": 32,
	"bos_token_id": 1,
	"dlm_loss_weight": null,
	"dlm_paradigm": "bidirectional",
	"dp_varying_mask_ratio": false,
	"eos_token_id": 2,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 9216,
	"mask_token_id": 100,
	"max_position_embeddings": 4096,
	"mlp_bias": false,
	"model_type": "nemotron_labs_diffusion",
	"num_attention_heads": 32,
	"num_hidden_layers": 26,
	"num_key_value_heads": 8,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"beta_fast": 32.0,
	"beta_slow": 1.0,
	"factor": 0.25,
	"llama_4_scaling_beta": 0.1,
	"mscale": 1.0,
	"mscale_all_dim": 1.0,
	"original_max_position_embeddings": 16384,
	"rope_theta": 1000000.0,
	"rope_type": "yarn"
	},
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "5.0.0",
	"use_cache": false,
	"vocab_size": 131072
	}