Xrenya/smolVLM

The model was trained on 491M tokens, but overall make decent predictions.

Example:

Generate output:

The image displays an indoor setting with a large, open-air display featuring a variety of clothing items. The display is positioned in front of a large, wooden sign with the text "UNIDO" in white letters, which is surrounded by a green background. The sign is positioned on a wooden floor, and the sign is adorned with a green and white banner with the text "UNIDO" in white letters.