Baguettotron-VLM extends PleIAs Baguettotron original language-only model with visual capabilities via InternViT-300M-448px-V2.5 vision encoder
🏗️ Building on HF
Andrea Gemelli
andreagemelli
AI & ML interests
Natural Language Processing, Computer Vision, Generative Models, Document Analysis
Recent Activity
published a model 1 day ago
andreagemelli/baguettotron-internvit-alignment published a model 1 day ago
andreagemelli/baguettotron-vision-vqa updated a model 1 day ago
andreagemelli/baguettotron-vision-vqa