A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.
Mark Marosi
Mapika
P(doom) 1%
AI & ML interests
NLP, Drug Discovery
Recent Activity
updated a dataset about 23 hours ago
Mapika/decision-index-results updated a model 1 day ago
Mapika/decider-31b published a model 1 day ago
Mapika/decider-31bOrganizations
models 15
Mapika/decider-31b
Text Classification • 21B • Updated • 23
Mapika/decider-12b
Text Classification • 12B • Updated • 311 • 4
Mapika/decider-chat-qwen3.6-27b
Text Classification • 28B • Updated • 49
Mapika/decider-chat-gemma4-31b
Text Classification • 31B • Updated • 485 • 3
Mapika/decider-2b-coherent
Multiple Choice • Updated • 43 • 1
Mapika/decider-2b-GGUF
Text Classification • 2B • Updated • 2.76k • 1
Mapika/decider-4b-GGUF
Text Classification • 4B • Updated • 4.77k • 3
Mapika/decider-2b
Text Classification • 2B • Updated • 330k • 102
Mapika/decider-4b
Text Classification • 4B • Updated • 25.3k • 26
Mapika/decider-35b-a3b
Text Classification • 35B • Updated • 1.61k • 9