metadata
base_model: LiquidAI/LFM2.5-VL-1.6B
description: >-
LFM2.5-VL 1.6B vision-language model from Liquid AI for image and text
understanding.
license: other
pipeline_tag: image-text-to-text
tags:
- vision
- text-embed
- image-embed
- apple-npu