Instructions to use fgho/trocr-hanseXVI-kurrent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fgho/trocr-hanseXVI-kurrent with Transformers:

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

pipe = pipeline("image-text-to-text", model="fgho/trocr-hanseXVI-kurrent")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("fgho/trocr-hanseXVI-kurrent")
model = AutoModelForMultimodalLM.from_pretrained("fgho/trocr-hanseXVI-kurrent")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fgho/trocr-hanseXVI-kurrent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fgho/trocr-hanseXVI-kurrent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fgho/trocr-hanseXVI-kurrent",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fgho/trocr-hanseXVI-kurrent

SGLang

How to use fgho/trocr-hanseXVI-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 "fgho/trocr-hanseXVI-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": "fgho/trocr-hanseXVI-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 "fgho/trocr-hanseXVI-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": "fgho/trocr-hanseXVI-kurrent",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fgho/trocr-hanseXVI-kurrent with Docker Model Runner:
```
docker model run hf.co/fgho/trocr-hanseXVI-kurrent
```

TrOCR Kurrent-Model Hanse 16th century

Handwritten Text Recognition model for historical Hanse sources 16th.

Model Description

Developed by: Research Centre for Hanse and Baltic History (FGHO, https://fgho.eu) in the Flow Project (https://flow-project.net)
Model type: TrOCR
Language(s) (NLP): Early New High German
Finetuned from model: dh-unibe/trocr-kurrent-XVI-XVII

Data Sources

fgho/hanse-kurrent-xvi-lines

Training Details

Epochs: 3.125/5 Best Eval CER: 0.049711

Downloads last month: 72

Safetensors

Model size

0.3B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support