YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Tempered-4B\n\nA 4B dense System-One decision model continued from Mapika/decider-4b v2. Training uses consensus-filtered hard decisions, real public supervised data, and frozen-v1-anchor replay distributions.\n\nTeacher models were used only to create/filter training data; they are not part of the deployed model.\n

Downloads last month
14
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support