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

Libraries

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

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

pipe = pipeline("image-text-to-text", model="nvidia/Nemotron-Labs-Diffusion-VLM-8B", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/Nemotron-Labs-Diffusion-VLM-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-VLM-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-VLM-8B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

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

SGLang

How to use nvidia/Nemotron-Labs-Diffusion-VLM-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-VLM-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-VLM-8B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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-VLM-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-VLM-8B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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

Nemotron-Labs-Diffusion-VLM-8B / config.json

YongganFu

Initial release of Nemotron-Labs-Diffusion-VLM-8B

c6706ba 3 days ago

raw

history blame contribute delete

2.89 kB

	{
	"ada_dlm_loss_ratio": null,
	"ada_perm_ratio_global": null,
	"ada_perm_ratio_per_block": null,
	"adaptive_mask_rate": false,
	"always_mask_im_end": false,
	"ar_loss_weight": 1.0,
	"architectures": [
	"NemotronLabsDiffusionVLMModel"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_implementation": null,
	"auto_map": {
	"AutoConfig": "configuration_nemotron_labs_diffusion_vlm.NemotronLabsDiffusionVLMConfig",
	"AutoModel": "modeling_nemotron_labs_diffusion_vlm.NemotronLabsDiffusionVLMModel",
	"AutoModelForCausalLM": "modeling_nemotron_labs_diffusion_vlm.NemotronLabsDiffusionVLMModel"
	},
	"block_size": 32,
	"bos_token_id": 1,
	"complementary_mask": true,
	"diff_loss_weight": 0.5,
	"dlm_arch": "encoder",
	"dlm_loss_weight": 0.5,
	"dlm_paradigm": "bidirectional",
	"dlm_type": "llada",
	"dp_varying_mask_ratio": false,
	"dtype": "bfloat16",
	"enforce_mask": false,
	"eos_token_id": 11,
	"global_loss_avg": true,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"im_end_token_id": 11,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"mask_token_id": 100,
	"max_position_embeddings": 262144,
	"mlp_bias": false,
	"model_type": "nemotron_labs_diffusion_vlm",
	"multi_sampling": null,
	"multimodal_projector_bias": false,
	"num_ar_layers": 0,
	"num_attention_heads": 32,
	"num_diffusion_layers": 0,
	"num_hidden_layers": 34,
	"num_key_value_heads": 8,
	"num_skip_loss_tokens": 0,
	"pad_token_id": 11,
	"prefix_ratio": 0.8,
	"projector_hidden_act": "gelu",
	"random_length_prob": 0,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"beta_fast": 32.0,
	"beta_slow": 1.0,
	"factor": 16.0,
	"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",
	"type": "yarn"
	},
	"rope_scaling": {
	"beta_fast": 32.0,
	"beta_slow": 1.0,
	"factor": 16.0,
	"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",
	"type": "yarn"
	},
	"rope_theta": 1000000.0,
	"sliding_window": null,
	"spatial_merge_size": 2,
	"tie_word_embeddings": false,
	"tok_mask_half_life_ratio": null,
	"transformers_version": "4.57.1",
	"use_cache": false,
	"vision_config": {
	"attention_dropout": 0.0,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 1024,
	"image_size": 1540,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"model_type": "pixtral",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"patch_size": 14,
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	}
	},
	"vision_feature_layer": -1,
	"vocab_size": 131073
	}