How it works
The private model
One model trained on every text record, inside the room.
A LoRA adapter (rank 8) on Qwen2.5 0.5B Instruct, trained every week on CPU inside the room on the live text records. Trap rows and deleted records are never trained on.
- Its weights never leave the room. It can only be called, never downloaded.
- A call costs 0.002 USDC and pays 100% to the owners whose text trained it, pro rata.
- First training as soon as 25 text records are uploaded. Until then
POST /api/modelrefuses for free.