4
TextSnap
📊
Florence 2 used in OCR to extract & visualize text
Zero-shot text classification using ModernBERT-large
Redefining Multimodal RAG with ColQwen2.5 (ColPali) & Gemini
Gemma 3: Google's multimodal, multilingual, long context LLM
Demo for MiniCPM-o 2.6 to answer questions about images