Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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

ademax
/
trocr-small-v3

Image-Text-to-Text
Transformers
PyTorch
ONNX
vision-encoder-decoder
Model card Files Files and versions
xet
Community

Instructions to use ademax/trocr-small-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use ademax/trocr-small-v3 with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("image-text-to-text", model="ademax/trocr-small-v3")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForMultimodalLM
    
    tokenizer = AutoTokenizer.from_pretrained("ademax/trocr-small-v3")
    model = AutoModelForMultimodalLM.from_pretrained("ademax/trocr-small-v3")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • vLLM

    How to use ademax/trocr-small-v3 with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "ademax/trocr-small-v3"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "ademax/trocr-small-v3",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    Use Docker
    docker model run hf.co/ademax/trocr-small-v3
  • SGLang

    How to use ademax/trocr-small-v3 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 "ademax/trocr-small-v3" \
        --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": "ademax/trocr-small-v3",
    		"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 "ademax/trocr-small-v3" \
            --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": "ademax/trocr-small-v3",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
  • Docker Model Runner

    How to use ademax/trocr-small-v3 with Docker Model Runner:

    docker model run hf.co/ademax/trocr-small-v3

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Gated model
You can list files but not access them

Preview of files found in this repository
  • .gitattributes
    1.52 kB
    initial commit over 2 years ago
  • added_tokens.json
    2.53 kB
    Upload processor over 2 years ago
  • config.json
    4.63 kB
    Upload model over 2 years ago
  • decoder_model.onnx
    102 MB
    xet
    Upload decoder_model.onnx with huggingface_hub over 2 years ago
  • encoder_model.onnx
    87.5 MB
    xet
    Upload encoder_model.onnx with huggingface_hub over 2 years ago
  • generation_config.json
    185 Bytes
    Upload model over 2 years ago
  • preprocessor_config.json
    504 Bytes
    Upload processor over 2 years ago
  • pytorch_model.bin

    Detected Pickle imports (3)

    • "collections.OrderedDict",
    • "torch.FloatStorage",
    • "torch._utils._rebuild_tensor_v2"

    What is a pickle import?

    189 MB
    xet
    Upload model over 2 years ago
  • special_tokens_map.json
    2.12 kB
    Upload processor over 2 years ago
  • spiece.model
    820 kB
    xet
    Upload processor over 2 years ago
  • tokenizer.json
    2.42 MB
    Upload processor over 2 years ago
  • tokenizer_config.json
    19.8 kB
    Upload processor over 2 years ago