PaddleOCR-VL
PaddleOCR-VL-1.6 is a compact document parsing vision-language model from PaddlePaddle for OCR, table, formula, chart, seal, and spotting tasks.
This guide shows how to fine-tune PaddleOCR-VL with Axolotl’s multimodal SFT path.
Getting Started
Install Axolotl following the installation guide.
Run one of the fine-tuning examples:
axolotl train examples/paddleocr-vl/paddleocr-vl-1_6-qlora.yamlaxolotl train examples/paddleocr-vl/paddleocr-vl-1_6-full-finetune.yaml
Tips
- The model uses its bundled chat template through
processor_type: AutoProcessor; no explicitchat_templateis needed. - Do not set
trust_remote_codefor this example; Axolotl’s pinned Transformers version includes the PaddleOCR-VL model and processor implementation. - Do not enable Liger or Cut Cross Entropy; neither path currently patches PaddleOCR-VL’s multimodal
ForConditionalGenerationclass. - PaddleOCR-VL task prompts include
OCR:,Table Recognition:,Formula Recognition:,Chart Recognition:,Seal Recognition:, andSpotting:. - Dataset rows should use Axolotl’s multimodal
messagesformat with image content in the user turn and the parsed text or markup in the assistant turn. - The QLoRA example targets the language decoder, vision encoder, and multimodal projector with LoRA adapters.