PaddleOCR-VL 1.6
Self-hosted mirror of PaddlePaddle/PaddleOCR-VL-1.6
(Apache-2.0), a vision-language OCR model used by the candle backend in
xberg. Weights are unmodified; every file is sha256-pinned in the
xberg source tree (crates/xberg/src/candle_ocr/paddleocr-vl-1.6.sha256) and verified at download.
Supported tasks: OCR, Table, Formula, Chart.
- Downloads last month
- 68
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support