A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.
Mark Marosi
Mapika
AI & ML interests
NLP, Drug Discovery
Recent Activity
new activity 2 days ago
Mapika/decider-4b:Independent run: our MNLI 0.7667 against your published 0.926 updated a model 2 days ago
Mapika/decider-2b