Instructions to use stepfun-ai/GOT-OCR-2.0-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/GOT-OCR-2.0-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="stepfun-ai/GOT-OCR-2.0-hf")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf")
model = AutoModelForMultimodalLM.from_pretrained("stepfun-ai/GOT-OCR-2.0-hf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stepfun-ai/GOT-OCR-2.0-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/GOT-OCR-2.0-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/GOT-OCR-2.0-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stepfun-ai/GOT-OCR-2.0-hf

SGLang

How to use stepfun-ai/GOT-OCR-2.0-hf 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 "stepfun-ai/GOT-OCR-2.0-hf" \
    --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": "stepfun-ai/GOT-OCR-2.0-hf",
		"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 "stepfun-ai/GOT-OCR-2.0-hf" \
        --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": "stepfun-ai/GOT-OCR-2.0-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stepfun-ai/GOT-OCR-2.0-hf with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/GOT-OCR-2.0-hf
```

Rendering - HELP

by pixelp1908 - opened Feb 27, 2025

Discussion

pixelp1908

Feb 27, 2025

As mentioned in the documentation of the model -
"""
the outputs can be further processed to render the desired format, with packages like pdftex, mathpix, matplotlib, tikz, verovio or pyecharts"""

It would be great if you can share an example code for the same!

Thanks

YanrenLin

Mar 10, 2025

•

edited Mar 10, 2025

Will this model be applied on a laptop with CPU ?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment