ZQTTTT

/

DOCR-Inspector-7B

like 0

This PR significantly enhances the model card for DOCR-Inspector-7B by:

• Updating the license to cc-by-nc-sa-4.0, as specified in the project's GitHub repository.
• Adding pipeline_tag: image-text-to-text to accurately categorize the model on the Hub.
• Specifying library_name: transformers to indicate compatibility with the Hugging Face Transformers library and enable the automated code snippet.
• Including a direct link to the paper: DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM.
• Adding a link to the official GitHub repository: https://github.com/ZZZZZQT/DOCR-Inspector.
• Expanding the model description with an introduction and key features from the GitHub README.
• Integrating details about the DOCRcase-200K and DOCRcaseBench datasets.
• Adding the comprehensive performance evaluation table.
• Including usage instructions, specifically the vLLM inference command as found in the GitHub README.
• Adding the correct BibTeX citation for proper attribution.

Please review and merge this PR if everything looks good.