Image-Text-to-Text
Transformers
PyTorch
Safetensors
German
vision-encoder-decoder
trocr
kurrent
ocr
htr
19th century
Instructions to use dh-unibe/trocr-kurrent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dh-unibe/trocr-kurrent with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="dh-unibe/trocr-kurrent")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("dh-unibe/trocr-kurrent") model = AutoModelForMultimodalLM.from_pretrained("dh-unibe/trocr-kurrent", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dh-unibe/trocr-kurrent with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dh-unibe/trocr-kurrent" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dh-unibe/trocr-kurrent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dh-unibe/trocr-kurrent
- SGLang
How to use dh-unibe/trocr-kurrent 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 "dh-unibe/trocr-kurrent" \ --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": "dh-unibe/trocr-kurrent", "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 "dh-unibe/trocr-kurrent" \ --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": "dh-unibe/trocr-kurrent", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dh-unibe/trocr-kurrent with Docker Model Runner:
docker model run hf.co/dh-unibe/trocr-kurrent
Commit History
Update README.md 6452b42 verified
added metadata aa21190 verified
Adding `safetensors` variant of this model (#1) 62bbd27 verified
small update 033b849
Update README.md ff805db
Update README.md 65460ed
Jonas Widmer commited on
Update README.md 3121d2c
Jonas Widmer commited on
Update README.md 4908a40
Jonas Widmer commited on
Update README.md 737006c
Jonas Widmer commited on
new model version 2a3575e
Jonas Widmer commited on
Update README.md e93cc39
Jonas Widmer commited on
Update README.md 4c632d1
Jonas Widmer commited on
Create README.md d7a0902
Jonas Widmer commited on
Init ac8bcba
Jonas Widmer commited on