Instructions to use raulss1/donut-base-sroie with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use raulss1/donut-base-sroie with Transformers:

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

pipe = pipeline("image-text-to-text", model="raulss1/donut-base-sroie")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("raulss1/donut-base-sroie")
model = AutoModelForMultimodalLM.from_pretrained("raulss1/donut-base-sroie", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use raulss1/donut-base-sroie with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "raulss1/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": "raulss1/donut-base-sroie",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/raulss1/donut-base-sroie

SGLang

How to use raulss1/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 "raulss1/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": "raulss1/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 "raulss1/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": "raulss1/donut-base-sroie",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use raulss1/donut-base-sroie with Docker Model Runner:
```
docker model run hf.co/raulss1/donut-base-sroie
```

donut-base-sroie

This model is a fine-tuned version of pandafm/donut-es on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8468
Cer: 1.4966
Exact Match: 0.0
Avg Edit Distance: 86.6638
Nombre/razón social Accuracy: 0.0
Factura Accuracy: 0.0
Base imponible Accuracy: 0.0
Total Accuracy: 0.0
Fecha Accuracy: 0.0
Igic Accuracy: 0.0
Cif Accuracy: 0.0
Nif Accuracy: 0.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Avg Edit Distance
8.4323	1.0	104	7.4595	7.3214	423.1932
5.9044	2.0	208	4.6216	7.2697	420.2077
2.564	3.0	312	2.2138	3.9204	226.6039
1.6145	4.0	416	1.4490	3.3625	194.3575
0.9462	5.0	520	1.1422	1.2631	73.0048
0.6649	6.0	624	0.9678	1.5508	89.6425
0.4795	7.0	728	0.9374	2.0241	117.0
0.3135	8.0	832	0.9448	1.0045	58.0628
0.2315	9.0	936	0.9376	0.8702	50.2995
0.1716	10.0	1040	0.9406	0.8119	46.9324
0.1297	11.0	1144	0.9584	0.7571	43.7681
0.0954	12.0	1248	0.9966	0.7495	43.3237
0.0792	13.0	1352	1.0172	0.8140	47.0531
0.0627	14.0	1456	1.0403	0.8982	51.9130

Framework versions

Transformers 4.57.0
Pytorch 2.4.1+cu121
Datasets 4.2.0
Tokenizers 0.22.1

Downloads last month: 22

Safetensors

Model size

0.2B params

Tensor type

I64

F32

Model tree for raulss1/donut-base-sroie

Base model

naver-clova-ix/donut-base-finetuned-cord-v2

Finetuned

pandafm/donut-es

Finetuned

(1)

this model