Instructions to use opendatalab/MinerU2.5-Pro-2605-1.2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use opendatalab/MinerU2.5-Pro-2605-1.2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="opendatalab/MinerU2.5-Pro-2605-1.2B")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("opendatalab/MinerU2.5-Pro-2605-1.2B")
model = AutoModelForMultimodalLM.from_pretrained("opendatalab/MinerU2.5-Pro-2605-1.2B")
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 Settings

vLLM

How to use opendatalab/MinerU2.5-Pro-2605-1.2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "opendatalab/MinerU2.5-Pro-2605-1.2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "opendatalab/MinerU2.5-Pro-2605-1.2B",
		"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/opendatalab/MinerU2.5-Pro-2605-1.2B

SGLang

How to use opendatalab/MinerU2.5-Pro-2605-1.2B 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 "opendatalab/MinerU2.5-Pro-2605-1.2B" \
    --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": "opendatalab/MinerU2.5-Pro-2605-1.2B",
		"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 "opendatalab/MinerU2.5-Pro-2605-1.2B" \
        --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": "opendatalab/MinerU2.5-Pro-2605-1.2B",
		"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 opendatalab/MinerU2.5-Pro-2605-1.2B with Docker Model Runner:
```
docker model run hf.co/opendatalab/MinerU2.5-Pro-2605-1.2B
```

Struggles with differentiating between different types of headers

by sumiremelody - opened 5 days ago

Discussion

sumiremelody

5 days ago

•

edited 5 days ago

When presented with PDFs of literature or textbooks, the model will:

Classify running headings as either headings or titles, making it harder to remove them from the output since they’re visual noise from the reader’s perspective
The heading levels don’t seem to follow any consistent pattern.

See how, in the above, both Table of Contents and Part 1. The Fundamentals of Machine Learning are treated as top-level headers. Only Table of Contents should have been treated as top-level.

In the above, the Preface header is just outright missing!

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