Instructions to use PaddlePaddle/HPD-Parsing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PaddlePaddle/HPD-Parsing with Transformers:

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

pipe = pipeline("image-text-to-text", model="PaddlePaddle/HPD-Parsing", 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("PaddlePaddle/HPD-Parsing", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PaddlePaddle/HPD-Parsing with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PaddlePaddle/HPD-Parsing"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PaddlePaddle/HPD-Parsing",
		"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/PaddlePaddle/HPD-Parsing

SGLang

How to use PaddlePaddle/HPD-Parsing 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 "PaddlePaddle/HPD-Parsing" \
    --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": "PaddlePaddle/HPD-Parsing",
		"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 "PaddlePaddle/HPD-Parsing" \
        --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": "PaddlePaddle/HPD-Parsing",
		"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 PaddlePaddle/HPD-Parsing with Docker Model Runner:
```
docker model run hf.co/PaddlePaddle/HPD-Parsing
```

ChengCui commited on 9 days ago

Commit

f3bfe25

verified ·

1 Parent(s): 7325252

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -71,7 +71,7 @@ We introduce **HPD-Parsing**, a lightweight (1B) and high-throughput document pa
 **🔄 Staged Adaptation with Automated Difficulty-Aware Data Curation**: We develop a staged adaptation strategy that transfers conventional autoregressive document parsing capabilities to the proposed hierarchical parallel decoding paradigm while preserving parsing accuracy. The strategy is supported by an automated difficulty-aware data curation pipeline that integrates large-scale data collection, model-assisted annotation, difficulty estimation, and balanced sampling. By progressively adapting the model and emphasizing challenging samples, the training framework mitigates the accuracy degradation caused by the transition to parallel decoding with minimal manual annotation effort.
-**⚡ State-of-the-Art Throughput with Competitive Parsing Accuracy**: HPD-Parsing achieves state-of-the-art inference efficiency on OmniDocBench v1.6, reaching a peak throughput of 4,752 Tokens Per Second (TPS). It delivers $1.62\times$ the throughput of the fastest existing document parsing model and more than $3.06\times$ that of its autoregressive baseline, while maintaining competitive parsing accuracy. These results demonstrate that document parsing can be effectively executed through global layout coordination and localized parallel decoding rather than a single sequential generation trajectory.
 ### **HPD-Parsing Architecture**

 **🔄 Staged Adaptation with Automated Difficulty-Aware Data Curation**: We develop a staged adaptation strategy that transfers conventional autoregressive document parsing capabilities to the proposed hierarchical parallel decoding paradigm while preserving parsing accuracy. The strategy is supported by an automated difficulty-aware data curation pipeline that integrates large-scale data collection, model-assisted annotation, difficulty estimation, and balanced sampling. By progressively adapting the model and emphasizing challenging samples, the training framework mitigates the accuracy degradation caused by the transition to parallel decoding with minimal manual annotation effort.
+**⚡ State-of-the-Art Throughput with Competitive Parsing Accuracy**: HPD-Parsing achieves state-of-the-art inference efficiency on OmniDocBench v1.6, reaching a peak throughput of 4,752 Tokens Per Second (TPS). It delivers 1.62x the throughput of the fastest existing document parsing model and more than 3.06x that of its autoregressive baseline, while maintaining competitive parsing accuracy. These results demonstrate that document parsing can be effectively executed through global layout coordination and localized parallel decoding rather than a single sequential generation trajectory.
 ### **HPD-Parsing Architecture**