PaddleOCR-VL
Collection
10 items • Updated • 2
How to use mlx-community/PaddleOCR-VL-8bit with PaddleOCR:
# See https://www.paddleocr.ai/latest/version3.x/pipeline_usage/PaddleOCR-VL.html to installation
from paddleocr import PaddleOCRVL
pipeline = PaddleOCRVL(pipeline_version="mlx-community/PaddleOCR-VL-8bit")
output = pipeline.predict("path/to/document_image.png")
for res in output:
res.print()
res.save_to_json(save_path="output")
res.save_to_markdown(save_path="output")How to use mlx-community/PaddleOCR-VL-8bit with MLX:
# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm
from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config
# Load the model
model, processor = load("mlx-community/PaddleOCR-VL-8bit")
config = load_config("mlx-community/PaddleOCR-VL-8bit")
# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."
# Apply chat template
formatted_prompt = apply_chat_template(
processor, config, prompt, num_images=1
)
# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)This model was converted to MLX format from PaddlePaddle/PaddleOCR-VL using mlx-vlm version 0.3.10.
Refer to the original model card for more details on the model.
pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/PaddleOCR-VL-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
8-bit
Base model
baidu/ERNIE-4.5-0.3B-Paddle