Instructions to use LFBMS/donut_complex_run5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LFBMS/donut_complex_run5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="LFBMS/donut_complex_run5")

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

tokenizer = AutoTokenizer.from_pretrained("LFBMS/donut_complex_run5")
model = AutoModelForMultimodalLM.from_pretrained("LFBMS/donut_complex_run5", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LFBMS/donut_complex_run5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LFBMS/donut_complex_run5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LFBMS/donut_complex_run5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LFBMS/donut_complex_run5

SGLang

How to use LFBMS/donut_complex_run5 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 "LFBMS/donut_complex_run5" \
    --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": "LFBMS/donut_complex_run5",
		"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 "LFBMS/donut_complex_run5" \
        --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": "LFBMS/donut_complex_run5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LFBMS/donut_complex_run5 with Docker Model Runner:
```
docker model run hf.co/LFBMS/donut_complex_run5
```

donut_complex_run5

Commit History

Apr 4, 2025

11:27
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
8ccc063

Feb 18, 2023

18:58
Training done

LFBMS

ba5ea7f
18:58
Training done

LFBMS

0f5afff
18:58
Training in progress, epoch 6

LFBMS

c5161c4
18:47
Training in progress, epoch 5

LFBMS

2a66196
18:37
Training in progress, epoch 4

LFBMS

91dc646
18:27
Training in progress, epoch 3

LFBMS

7920183
18:16
Training in progress, epoch 2

LFBMS

da779f0
18:06
Training in progress, epoch 1

LFBMS

19f4954
17:53
Training in progress, epoch 0

LFBMS

2885703
17:52
initial commit

LFBMS

ae93bbe

Commit History

Apr 4, 2025

Adding `safetensors` variant of this model⁠

Feb 18, 2023

Training done

Training done

Training in progress, epoch 6

Training in progress, epoch 5

Training in progress, epoch 4

Training in progress, epoch 3

Training in progress, epoch 2

Training in progress, epoch 1

Training in progress, epoch 0

initial commit