Instructions to use nvidia/NVIDIA-Nemotron-Parse-v1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-Parse-v1.2 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-v1.2", 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-v1.2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/NVIDIA-Nemotron-Parse-v1.2 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-v1.2"
# 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-v1.2",
		"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-v1.2

SGLang

How to use nvidia/NVIDIA-Nemotron-Parse-v1.2 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-v1.2" \
    --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-v1.2",
		"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-v1.2" \
        --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-v1.2",
		"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-v1.2 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-Parse-v1.2
```

Update with support for transformers 5.x compatibility

by nvidia-oliver-holworthy - opened 27 days ago

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+2637

-34

nvidia-oliver-holworthy

NVIDIA org 27 days ago

•

edited 26 days ago

This PR updates the custom Nemotron Parse decoder to work with both the legacy Transformers 4.x cache API and the newer 4.57/5.x cache interfaces, including MBartDecoderLayer signature differences and generation input handling. It also adds a reproducible uv + Docker test environment and a golden regression suite with captured reference outputs, so future dependency upgrades can be checked against the current 4.51.3 baseline.

What changed

Added compatibility handling in hf_nemotron_parse_modeling.py for legacy tuple-based KV caches and newer Cache / EncoderDecoderCache flows.
Added prepare_inputs_for_generation support so cached decoding works correctly during generation.
Added pyproject.toml, Dockerfile, and docker-compose.yaml for a reproducible GPU-backed test environment.
Added test_golden.py and golden_outputs.json to validate preprocessing, encoder outputs, decoder logits, generation, and processor behavior against known-good outputs.

Testing

python test_golden.py --capture
pytest test_golden.py -v

Fix MBartDecoderLayer forward pass for transformers 5.x compatibility382fc3a2

Add golden regression tests and Docker test environmente9fb5317

emelryan

NVIDIA org 26 days ago

Double checked this with your tests as well as an omnidocbench run and got consistent results between old branch and new branch on transformers 4.x and 5.x. Looks good

emelryan changed pull request status to open 26 days ago

emelryan changed pull request status to merged 25 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment