Doğukan
@DogukanUrker
running d1-3B on a single RTX 3060. 12GB VRAM. (config below)
88.4% on BoolQ (full val, 3,270 questions), Liquid's card says 86.7. 44.5% on MMLU-Pro (all 12,032, random is 10%). ~43 ms p50 per decision, 21-23 decisions/s, 5 GB VRAM.
GPQA lands at 29.8%, close to random, which
88.4% on BoolQ (full val, 3,270 questions), Liquid's card says 86.7. 44.5% on MMLU-Pro (all 12,032, random is 10%). ~43 ms p50 per decision, 21-23 decisions/s, 5 GB VRAM.
GPQA lands at 29.8%, close to random, which
Liquid AI@liquidai · Oct 7Today we release Open d1: two open-weight multimodal models in our d1 decision model family.
> d1-3B: text + vision
> d1-omni-600M: text + image or text + audio
> Real-time decision making anywhere, from data centers such as @nvidia DGX to RTX workstations to Jetson at the edge.
> d1-3B: text + vision
> d1-omni-600M: text + image or text + audio
> Real-time decision making anywhere, from data centers such as @nvidia DGX to RTX workstations to Jetson at the edge.
Open quoted post →
2 36