prithivMLmods/Camel-Doc-OCR-062825

VISIONPricing:Input $0.4 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:32kPublished:Jun 24, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The prithivMLmods/Camel-Doc-OCR-062825 is a 7 billion parameter vision-language model, fine-tuned from Qwen2.5-VL-7B-Instruct, with a 32768 token context length. It specializes in document retrieval, content extraction, and analysis recognition, leveraging focused training on the Opendoc2-Analysis-Recognition dataset. This model excels at understanding complex document structures, extracting both structured and unstructured content, and interpreting visual data representations like charts and tables.

Loading preview...

Camel-Doc-OCR-062825: Advanced Document AI

The Camel-Doc-OCR-062825 model is a specialized 7 billion parameter vision-language model, fine-tuned from the Qwen2.5-VL-7B-Instruct architecture. It is specifically optimized for advanced document processing tasks, including retrieval, content extraction, and analysis recognition. This model enhances document comprehension by focusing on context-aware multimodal extraction and linking within complex document structures, trained on the Opendoc2-Analysis-Recognition dataset.

Key Capabilities

  • Context-Aware Multimodal Extraction: Understands document context and links multimodal elements.
  • Enhanced Document Retrieval: Efficiently locates and extracts relevant information from complex layouts.
  • Superior Content Extraction: Precisely extracts structured and unstructured content from diverse formats.
  • Analysis Recognition: Interprets analytical content, charts, tables, and visual data representations.
  • Competitive Performance: Achieves strong results on OCR and visual QA benchmarks such as DocVQA, MathVista, RealWorldQA, and MTVQA.
  • Video Understanding: Supports detailed comprehension of long-duration videos (up to 20+ minutes) for summarization and multi-modal reasoning.
  • Visually-Grounded Device Interaction: Enables mobile/robotic operation through visual inputs and text instructions.

Good for

  • High-fidelity document retrieval and content extraction.
  • Analysis recognition of charts, graphs, tables, and visual data.
  • Document-based question answering in educational and enterprise settings.
  • Extraction and LaTeX formatting of mathematical expressions.
  • Retrieval and summarization from long, multi-modal documents.
  • Multilingual document analysis and structured content extraction.
  • Robotic or mobile automation requiring vision-guided contextual interaction.

Finetunes
2 models