prithivMLmods/docscopeOCR-7B-050425-exp

VISIONPricing:Input $0.4 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:32kPublished:May 3, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The prithivMLmods/docscopeOCR-7B-050425-exp model is a 7 billion parameter vision-language model, fine-tuned from Qwen/Qwen2.5-VL-7B-Instruct, with a 32768 token context length. It specializes in Document-Level Optical Character Recognition (OCR), long-context vision-language understanding, and accurate image-to-text conversion with mathematical LaTeX formatting. This model excels at extracting structured content from complex documents and performing visual reasoning across diverse input formats. It achieves competitive results on OCR and visual QA benchmarks such as DocVQA, MathVista, RealWorldQA, and MTVQA.

Loading preview...

Overview

The prithivMLmods/docscopeOCR-7B-050425-exp is a 7 billion parameter vision-language model, fine-tuned from the Qwen2.5-VL architecture. It is specifically optimized for advanced Document-Level Optical Character Recognition (OCR), long-context vision-language understanding, and precise image-to-text conversion, including mathematical LaTeX formatting. The model is designed to handle complex, multi-page documents and dense visual layouts, providing coherent cross-reference understanding.

Key Capabilities

  • Advanced Document-Level OCR: Extracts structured content from diverse documents like invoices, academic papers, and forms.
  • Enhanced Long-Context Vision-Language Understanding: Processes long sequences of embedded text, tables, and diagrams within documents.
  • Competitive Performance: Achieves strong results on benchmarks such as DocVQA, MathVista, RealWorldQA, and MTVQA.
  • Video Understanding: Supports detailed comprehension of videos up to 20+ minutes for summarization and multi-modal reasoning.
  • Visually-Grounded Device Interaction: Enables mobile/robotic device operation through visual inputs and text instructions.

Intended Use Cases

  • High-fidelity OCR for various printed and scanned materials.
  • Image and document-based question answering for educational and enterprise applications.
  • Extraction and LaTeX formatting of mathematical expressions.
  • Retrieval and summarization from long documents and multi-modal inputs.
  • Multilingual OCR and structured content extraction.
  • Robotic or mobile automation requiring vision-guided contextual interaction.

Finetunes
2 models