Instructions to use strangervisionhf/paddle.ocr_path_expose with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use strangervisionhf/paddle.ocr_path_expose with Transformers:

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

pipe = pipeline("image-text-to-text", model="strangervisionhf/paddle.ocr_path_expose")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("strangervisionhf/paddle.ocr_path_expose", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use strangervisionhf/paddle.ocr_path_expose with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/strangervisionhf/paddle.ocr_path_expose

SGLang

How to use strangervisionhf/paddle.ocr_path_expose 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 "strangervisionhf/paddle.ocr_path_expose" \
    --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": "strangervisionhf/paddle.ocr_path_expose",
		"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 "strangervisionhf/paddle.ocr_path_expose" \
        --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": "strangervisionhf/paddle.ocr_path_expose",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use strangervisionhf/paddle.ocr_path_expose with Docker Model Runner:
```
docker model run hf.co/strangervisionhf/paddle.ocr_path_expose
```

prithivMLmods commited on Oct 24, 2025

Commit

bdcf08a

verified ·

1 Parent(s): f54d423

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -0

README.md CHANGED Viewed

@@ -4,3 +4,12 @@ license: apache-2.0
 > [!important]
 This is the OCR weight component of the [PaddlePaddle/PaddleOCR-VL](https://huggingface.co/PaddlePaddle/PaddleOCR-VL) model. These weights cannot be used for other use cases. If you wish to do so, please visit the original model page!

 > [!important]
 This is the OCR weight component of the [PaddlePaddle/PaddleOCR-VL](https://huggingface.co/PaddlePaddle/PaddleOCR-VL) model. These weights cannot be used for other use cases. If you wish to do so, please visit the original model page!
+> This repository directly exposes the OCR-only weights for smoother transformers implementation of the PaddleOCR-VL model.
+> [!note]
+Last updated: 4:00 AM (IST), October 25, 2025.
+> [!note]
+The latest transformers version used as of the above date is `transformers==4.57.1` and the torch version `2.8.0+cu126`