Show HN: VisionLaya: Jev with Vision capabilities
By someguy101010 · 2026-09-19 · 1 points · 0 comments
https://huggingface.co/thaitea/laya-vision-smolvlm-256m
This model makes calibrated, typed decisions about an image plus optional text. It answers choice, score and noul (yes/no probability) questions in one forward pass, with no text generation. It adds image input to Laya by replacing Laya's ModernBERT encoder with SmolVLM-256…
Open the full discussion on BetterNews