Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

openbmb
/
MiniCPM-OCR-1.0-AWQ

Image-Text-to-Text
Safetensors
English
Chinese
minicpm_ocr
minicpm-ocr
ocr
document-parsing
multimodal
awq
4-bit precision
quantized
conversational
Model card Files Files and versions
xet
Community

Instructions to use openbmb/MiniCPM-OCR-1.0-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Local Apps Settings
  • vLLM

    How to use openbmb/MiniCPM-OCR-1.0-AWQ with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "openbmb/MiniCPM-OCR-1.0-AWQ"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/chat/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "openbmb/MiniCPM-OCR-1.0-AWQ",
    		"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/openbmb/MiniCPM-OCR-1.0-AWQ
  • SGLang

    How to use openbmb/MiniCPM-OCR-1.0-AWQ 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 "openbmb/MiniCPM-OCR-1.0-AWQ" \
        --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": "openbmb/MiniCPM-OCR-1.0-AWQ",
    		"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 "openbmb/MiniCPM-OCR-1.0-AWQ" \
            --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": "openbmb/MiniCPM-OCR-1.0-AWQ",
    		"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 openbmb/MiniCPM-OCR-1.0-AWQ with Docker Model Runner:

    docker model run hf.co/openbmb/MiniCPM-OCR-1.0-AWQ
MiniCPM-OCR-1.0-AWQ
1.89 GB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 17 commits
asdfasdfqrqwer's picture
asdfasdfqrqwer
Restore top navigation and remove the hero image from the model card.
f9551d8 about 10 hours ago
  • .gitattributes
    2.21 kB
    docs: sync with latest GitHub about 11 hours ago
  • README.md
    14.2 kB
    Restore top navigation and remove the hero image from the model card. about 10 hours ago
  • chat_template.jinja
    7.34 kB
    init: quantized weights 3 days ago
  • config.json
    2.61 kB
    Update config.json about 12 hours ago
  • generation_config.json
    133 Bytes
    Update generation_config.json about 12 hours ago
  • model.safetensors
    1.87 GB
    xet
    init: quantized weights 3 days ago
  • preprocessor_config.json
    340 Bytes
    config: align with main repo (native minicpm_ocr, tf 5.21) about 11 hours ago
  • processor_config.json
    46 Bytes
    config: align with main repo (native minicpm_ocr, tf 5.21) about 11 hours ago
  • tokenizer.json
    20 MB
    xet
    init: quantized weights 3 days ago
  • tokenizer_config.json
    1.46 kB
    init: quantized weights 3 days ago