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

Libraries

How to use MerlinRichter/donut-base-sroie with Transformers:

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

pipe = pipeline("image-text-to-text", model="MerlinRichter/donut-base-sroie")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("MerlinRichter/donut-base-sroie")
model = AutoModelForImageTextToText.from_pretrained("MerlinRichter/donut-base-sroie")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MerlinRichter/donut-base-sroie with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MerlinRichter/donut-base-sroie

SGLang

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

Docker Model Runner
How to use MerlinRichter/donut-base-sroie with Docker Model Runner:
```
docker model run hf.co/MerlinRichter/donut-base-sroie
```

donut-base-sroie / tokenizer_config.json

MerlinRichter

End of training

e295560 over 2 years ago

raw

history blame contribute delete

7.15 kB

	{
	"added_tokens_decoder": {
	"0": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<pad>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"3": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57521": {
	"content": "<mask>",
	"lstrip": true,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57522": {
	"content": "<sep/>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"57523": {
	"content": "<s_iitcdip>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57524": {
	"content": "<s_synthdog>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57525": {
	"content": "</s_Ort>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57526": {
	"content": "</s_Addresse>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57527": {
	"content": "<s_Nachname>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57528": {
	"content": "<s_versicherungsnr>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57529": {
	"content": "</s_Krankenkasse>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57530": {
	"content": "<s_geburts datum>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57531": {
	"content": "<s_Satus>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57532": {
	"content": "</s_oben rechts>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57533": {
	"content": "<s_Datum>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57534": {
	"content": "</s_Vorname>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57535": {
	"content": "<s_Arzt nummer>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57536": {
	"content": "</s_Nachname>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57537": {
	"content": "<s_Betriebsstätten nummer>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57538": {
	"content": "</s_Arzt nummer>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57539": {
	"content": "<s_Konstenträgerkennung>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57540": {
	"content": "</s_versicherungsnr>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57541": {
	"content": "</s_Satus>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57542": {
	"content": "<s_Addresse>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57543": {
	"content": "</s_geburts datum>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57544": {
	"content": "<s_Ort>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57545": {
	"content": "</s_Datum>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57546": {
	"content": "</s_Konstenträgerkennung>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57547": {
	"content": "<s_Krankenkasse>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57548": {
	"content": "<s_Vorname>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57549": {
	"content": "<s_oben rechts>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57550": {
	"content": "</s_Betriebsstätten nummer>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [
	"</s_Ort>",
	"</s_Addresse>",
	"<s_Nachname>",
	"<s_versicherungsnr>",
	"</s_Krankenkasse>",
	"<s_geburts datum>",
	"<s_Satus>",
	"</s_oben rechts>",
	"<s_Datum>",
	"</s_Vorname>",
	"<s_Arzt nummer>",
	"</s_Nachname>",
	"<s_Betriebsstätten nummer>",
	"</s_Arzt nummer>",
	"<s_Konstenträgerkennung>",
	"</s_versicherungsnr>",
	"</s_Satus>",
	"<s_Addresse>",
	"</s_geburts datum>",
	"<s_Ort>",
	"<s>",
	"</s_Datum>",
	"</s_Konstenträgerkennung>",
	"<s_Krankenkasse>",
	"<s_Vorname>",
	"<s_oben rechts>",
	"</s_Betriebsstätten nummer>",
	"</s>"
	],
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": true,
	"cls_token": "<s>",
	"eos_token": "</s>",
	"mask_token": "<mask>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<pad>",
	"processor_class": "DonutProcessor",
	"sep_token": "</s>",
	"sp_model_kwargs": {},
	"tokenizer_class": "XLMRobertaTokenizer",
	"unk_token": "<unk>"
	}