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

Libraries

How to use colorlessideas/donut-chaghatay with Transformers:

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

pipe = pipeline("image-text-to-text", model="colorlessideas/donut-chaghatay")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("colorlessideas/donut-chaghatay")
model = AutoModelForImageTextToText.from_pretrained("colorlessideas/donut-chaghatay")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use colorlessideas/donut-chaghatay with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/colorlessideas/donut-chaghatay

SGLang

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

Docker Model Runner
How to use colorlessideas/donut-chaghatay with Docker Model Runner:
```
docker model run hf.co/colorlessideas/donut-chaghatay
```

donut-chaghatay

This model is a fine-tuned version of naver-clova-ix/donut-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1546
Cer: 40.6247
Wer: 14.7183

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.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_steps: 50
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
No log	1.0	19	9.0509	25.1059	2.7158
No log	2.0	38	6.2598	42.5651	16.0908
10.5392	3.0	57	1.5611	42.6418	13.8767
10.5392	4.0	76	0.2201	41.5395	14.4033
10.5392	5.0	95	0.1759	41.3522	14.2467
0.6735	6.0	114	0.1644	40.6622	14.8933
0.6735	7.0	133	0.1613	41.3281	14.815
0.1093	8.0	152	0.1533	40.2847	15.1208
0.1093	9.0	171	0.1548	40.6381	15.0767
0.1093	10.0	190	0.1546	40.6247	14.7183

Framework versions

Transformers 4.52.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 1

Safetensors

Model size

0.2B params

Tensor type

I64

F32

Inference Providers NEW

Image-Text-to-Text

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

Model tree for colorlessideas/donut-chaghatay

Base model

naver-clova-ix/donut-base

Finetuned

(483)

this model