Instructions to use to-be/Pix2StructGhega with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use to-be/Pix2StructGhega with Transformers:

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

pipe = pipeline("image-text-to-text", model="to-be/Pix2StructGhega")

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

processor = AutoProcessor.from_pretrained("to-be/Pix2StructGhega")
model = AutoModelForMultimodalLM.from_pretrained("to-be/Pix2StructGhega", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use to-be/Pix2StructGhega with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "to-be/Pix2StructGhega"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "to-be/Pix2StructGhega",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/to-be/Pix2StructGhega

SGLang

How to use to-be/Pix2StructGhega 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 "to-be/Pix2StructGhega" \
    --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": "to-be/Pix2StructGhega",
		"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 "to-be/Pix2StructGhega" \
        --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": "to-be/Pix2StructGhega",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use to-be/Pix2StructGhega with Docker Model Runner:
```
docker model run hf.co/to-be/Pix2StructGhega
```

Pix2StructGhega

Commit History

Jul 29, 2025

13:03
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
12e8ff2

Aug 4, 2023

12:59
Training done

to-be

e113059
12:51
Training done

to-be

f1a0042

Jun 12, 2023

20:58
Training done

to-be

e76ac98

Jun 9, 2023

11:14
Training done

to-be

0ffa746
11:13
Training done

to-be

cfe4e39
08:22
Training started

to-be

45f7775
08:17
Training started

to-be

f6d62a8
08:17
initial commit

to-be

93b39e9

Commit History

Jul 29, 2025

Adding `safetensors` variant of this model⁠

Aug 4, 2023

Training done

Training done

Jun 12, 2023

Training done

Jun 9, 2023

Training done

Training done

Training started

Training started

initial commit