Instructions to use ZQTTTT/DOCR-Inspector-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZQTTTT/DOCR-Inspector-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ZQTTTT/DOCR-Inspector-7B")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("ZQTTTT/DOCR-Inspector-7B")
model = AutoModelForImageTextToText.from_pretrained("ZQTTTT/DOCR-Inspector-7B")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ZQTTTT/DOCR-Inspector-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZQTTTT/DOCR-Inspector-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZQTTTT/DOCR-Inspector-7B",
		"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/ZQTTTT/DOCR-Inspector-7B

SGLang

How to use ZQTTTT/DOCR-Inspector-7B 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 "ZQTTTT/DOCR-Inspector-7B" \
    --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": "ZQTTTT/DOCR-Inspector-7B",
		"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 "ZQTTTT/DOCR-Inspector-7B" \
        --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": "ZQTTTT/DOCR-Inspector-7B",
		"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 ZQTTTT/DOCR-Inspector-7B with Docker Model Runner:
```
docker model run hf.co/ZQTTTT/DOCR-Inspector-7B
```

Improve model card: add metadata, paper/GitHub links, performance, and usage

by nielsr HF Staff - opened Dec 12, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+239

-3

nielsr

Dec 12, 2025

This PR significantly enhances the model card for DOCR-Inspector-7B by:

Updating the license to cc-by-nc-sa-4.0, as specified in the project's GitHub repository.
Adding pipeline_tag: image-text-to-text to accurately categorize the model on the Hub.
Specifying library_name: transformers to indicate compatibility with the Hugging Face Transformers library and enable the automated code snippet.
Including a direct link to the paper: DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM.
Adding a link to the official GitHub repository: https://github.com/ZZZZZQT/DOCR-Inspector.
Expanding the model description with an introduction and key features from the GitHub README.
Integrating details about the DOCRcase-200K and DOCRcaseBench datasets.
Adding the comprehensive performance evaluation table.
Including usage instructions, specifically the vLLM inference command as found in the GitHub README.
Adding the correct BibTeX citation for proper attribution.

Please review and merge this PR if everything looks good.

Improve model card: add metadata, paper/GitHub links, performance, and usagebcc8697d

ZQTTTT changed pull request status to merged Dec 13, 2025

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