Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

microsoft
/
udop-large

Image-Text-to-Text
Transformers
Safetensors
udop
vision
Model card Files Files and versions
xet
Community
10

Instructions to use microsoft/udop-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use microsoft/udop-large with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("image-text-to-text", model="microsoft/udop-large")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForImageTextToText
    
    processor = AutoProcessor.from_pretrained("microsoft/udop-large")
    model = AutoModelForImageTextToText.from_pretrained("microsoft/udop-large")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • vLLM

    How to use microsoft/udop-large with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "microsoft/udop-large"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "microsoft/udop-large",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    Use Docker
    docker model run hf.co/microsoft/udop-large
  • SGLang

    How to use microsoft/udop-large 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 "microsoft/udop-large" \
        --host 0.0.0.0 \
        --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "microsoft/udop-large",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    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 "microsoft/udop-large" \
            --host 0.0.0.0 \
            --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "microsoft/udop-large",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
  • Docker Model Runner

    How to use microsoft/udop-large with Docker Model Runner:

    docker model run hf.co/microsoft/udop-large
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Flash attention for udop large

1
#8 opened almost 2 years ago by
Vasanth2002

Worse results on NER tags than LayoultLMv3

3
#7 opened about 2 years ago by
hal9003

Unable to use pipeline

1
#5 opened about 2 years ago by
prajwalJumde

How to extract sections from a text

2
#4 opened about 2 years ago by
mihaigheorghe

Couldnt import UdopProcessor' from 'transformers'

1
#3 opened about 2 years ago by
himasai9711

Provide more information on how to use for image text extraction?

๐Ÿ‘ 1
5
#2 opened about 2 years ago by
Harsha-Sai

What is the license?

๐Ÿ‘ 1
#1 opened about 2 years ago by
to-be
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs