Instructions to use nvidia/NVIDIA-Nemotron-Parse-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-Parse-2.0 with Transformers:

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

pipe = pipeline("image-text-to-text", model="nvidia/NVIDIA-Nemotron-Parse-2.0", 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/NVIDIA-Nemotron-Parse-2.0", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-Parse-2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/NVIDIA-Nemotron-Parse-2.0"
# 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-Parse-2.0",
		"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/NVIDIA-Nemotron-Parse-2.0

SGLang

How to use nvidia/NVIDIA-Nemotron-Parse-2.0 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-Parse-2.0" \
    --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-Parse-2.0",
		"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/NVIDIA-Nemotron-Parse-2.0" \
        --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-Parse-2.0",
		"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/NVIDIA-Nemotron-Parse-2.0 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-Parse-2.0
```

NVIDIA-Nemotron-Parse-2.0 / explainability.md

emelryan

Initial release artifacts

2a82cb1 about 15 hours ago

preview code

Raw

History Blame Contribute Delete

2.57 kB

	## Explainability

	Field \| Response
	:---- \| :----
	Intended Task/Domain: \| Document understanding, OCR, layout parsing, table extraction, and text extraction with spatial grounding.
	Model Type: \| Transformer-based vision-encoder-decoder model.
	Intended Users: \| Developers and teams building document intelligence, retrieval-augmented generation (RAG), data-curation, extraction, and multimodal agent workflows.
	Output: \| Structured text containing document element classes, bounding boxes, reading-order information, chart/table annotations, and extracted text.
	(For GPAI Models): Tools used to evaluate datasets to identify synthetic data and ensure data authenticity. \| Internal dataset provenance checks, dataset audits, synthetic-data source tracking, and qualitative review.
	Describe how the model works: \| NVIDIA Nemotron Parse 2.0 encodes an input document image with a vision encoder, compresses visual features with an adapter, and uses a text decoder conditioned on task prompt tokens to generate structured document annotations. The 2.0 tokenizer includes an approximately 20k-token multilingual vocabulary expansion and chart-aware output support through the `<class_Chart>` class token.
	Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: \| Not Applicable
	Technical Limitations & Mitigation: \| Performance can vary for low-resolution scans, motion blur, handwriting, decorative fonts, dense tables, unusual layouts, unsupported languages or scripts, and documents with heavy compression artifacts. Users should evaluate outputs on representative documents and use human review for high-impact workflows.
	Verified to have met prescribed NVIDIA quality standards: \| Yes
	Performance Metrics: \| OCR accuracy, layout/class accuracy, table extraction quality, chart extraction quality, reading-order quality, grounding quality, latency, throughput, and qualitative visual inspection.
	Potential Known Risks: \| The model may miss text, hallucinate structure, assign incorrect classes, produce inaccurate bounding boxes, or incorrectly order elements. Downstream systems should treat output as model-generated extraction results and apply validation, confidence checks, and human review where appropriate.
	Licensing: \| Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Use of the tokenizer included in this model is governed by the [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/).

	## Explainability

	Field \| Response
	:---- \| :----
	Intended Task/Domain: \| Document understanding, OCR, layout parsing, table extraction, and text extraction with spatial grounding.
	Model Type: \| Transformer-based vision-encoder-decoder model.
	Intended Users: \| Developers and teams building document intelligence, retrieval-augmented generation (RAG), data-curation, extraction, and multimodal agent workflows.
	Output: \| Structured text containing document element classes, bounding boxes, reading-order information, chart/table annotations, and extracted text.
	(For GPAI Models): Tools used to evaluate datasets to identify synthetic data and ensure data authenticity. \| Internal dataset provenance checks, dataset audits, synthetic-data source tracking, and qualitative review.
	Describe how the model works: \| NVIDIA Nemotron Parse 2.0 encodes an input document image with a vision encoder, compresses visual features with an adapter, and uses a text decoder conditioned on task prompt tokens to generate structured document annotations. The 2.0 tokenizer includes an approximately 20k-token multilingual vocabulary expansion and chart-aware output support through the `<class_Chart>` class token.
	Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: \| Not Applicable
	Technical Limitations & Mitigation: \| Performance can vary for low-resolution scans, motion blur, handwriting, decorative fonts, dense tables, unusual layouts, unsupported languages or scripts, and documents with heavy compression artifacts. Users should evaluate outputs on representative documents and use human review for high-impact workflows.
	Verified to have met prescribed NVIDIA quality standards: \| Yes
	Performance Metrics: \| OCR accuracy, layout/class accuracy, table extraction quality, chart extraction quality, reading-order quality, grounding quality, latency, throughput, and qualitative visual inspection.
	Potential Known Risks: \| The model may miss text, hallucinate structure, assign incorrect classes, produce inaccurate bounding boxes, or incorrectly order elements. Downstream systems should treat output as model-generated extraction results and apply validation, confidence checks, and human review where appropriate.
	Licensing: \| Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Use of the tokenizer included in this model is governed by the [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/).