x.comthreadMarktechpost AI (@Marktechpost) on X
Liquid AI released Open d1, two open-weight "decision models" — d1-3B (text + vision) and d1-omni-600M (text + image or text + audio) — that don't generate text tokens at all. Instead they take a state plus a typed question as input and return calibrated probabilities in a single forward pass, positioning them as lightweight classifiers/judges rather than generative LLMs.
TL;DR Liquid AI open-sources Open d1, token-free multimodal "decision models" (d1-3B, d1-omni-600M) that output calibrated probabilities instead of generated text.
Organisations named here
Technologies named here
Related in models
