Instructions to use Riksarkivet/donut-base-hist-swe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Riksarkivet/donut-base-hist-swe with Transformers:

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

pipe = pipeline("image-text-to-text", model="Riksarkivet/donut-base-hist-swe")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("Riksarkivet/donut-base-hist-swe")
model = AutoModelForImageTextToText.from_pretrained("Riksarkivet/donut-base-hist-swe")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Riksarkivet/donut-base-hist-swe with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Riksarkivet/donut-base-hist-swe

SGLang

How to use Riksarkivet/donut-base-hist-swe 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 "Riksarkivet/donut-base-hist-swe" \
    --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": "Riksarkivet/donut-base-hist-swe",
		"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 "Riksarkivet/donut-base-hist-swe" \
        --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": "Riksarkivet/donut-base-hist-swe",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Riksarkivet/donut-base-hist-swe with Docker Model Runner:
```
docker model run hf.co/Riksarkivet/donut-base-hist-swe
```

BETA Historical Swedish Donut

This model extends the base training of naver-clova-ix/donut-base with a "learn to read" training phase focused on historical handwritten Swedish. It has been trained on transcribing paragraphs of 1-15 lines of handwritten text sourced from documents from the period 1600-1900. The model needs to be finetuned for downstream use.

This model is still under development.

Known issues

The model has a tendency to produce empty transcriptions of shorter paragraphs (1-5 lines).

Training data

The training data was sourced from Riksarkivet's HTR training data (most of which can be found here on HuggingFace) and the Norhand v3 dataset.

Downloads last month: 13

Inference Providers NEW

Image-Text-to-Text

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