Churro Collection Dataset and model for handwritten and print text recognition in historical documents • 3 items • Updated Sep 27 • 2
view article Article ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases Nov 5 • 57
Running on L40S 37 NuMarkdown 8b Thinking 👁 37 Reasoning model specialized for OCR/Markdown generation.
SauerkrautLM-Multilingual-(Reason)-ColBERT Collection SauerkrautLM ColBERT is a suite of Late-Interaction retrieval models built with PyLate’s ColBERT architecture and tuned for seven European languages. • 7 items • Updated Aug 3 • 20
view article Article System Prompt Learning: Teaching LLMs to Learn Problem-Solving Strategies from Experience Jun 2 • 23
Running on Zero Featured 72 ColPali fine-tuning Query Generator 🔍 72 Generate document retrieval queries from an image
Parallia/Fairly-Multilingual-ModernBERT-Embed-BE Sentence Similarity • 0.3B • Updated Jan 14 • 43 • 27
view article Article Introducing Synthetic Data Workshop: Your Gateway to Easy Synthetic Dataset Creation Jun 20, 2024 • 12