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
updated a model 41 minutes ago
Mapika/decider-chat-qwen3.6-27b published a model 41 minutes ago
Mapika/decider-chat-qwen3.6-27b updated a model 41 minutes ago
Mapika/decider-chat-gemma4-31bOrganizations
models 14
Mapika/decider-chat-qwen3.6-27b
Text Classification • 28B • Updated
Mapika/decider-chat-gemma4-31b
Text Classification • 31B • Updated
Mapika/decider-12b
Text Classification • 12B • Updated
Mapika/decider-2b-coherent
Multiple Choice • Updated • 17
Mapika/decider-2b-GGUF
Text Classification • 2B • Updated • 689
Mapika/decider-4b-GGUF
Text Classification • 4B • Updated • 935 • 1
Mapika/decider-2b
Text Classification • 2B • Updated • 244k • 94
Mapika/decider-4b
Text Classification • 4B • Updated • 5.89k • 11
Mapika/decider-35b-a3b
Text Classification • 35B • Updated • 909 • 8
Mapika/decider-35b-a3b-nvfp4
Text Classification • 18B • Updated • 637 • 7