Typesafe/system One Api-compatible Local Model Endpoint

Kev trains LoRA adapters plus a pointer readout head on Qwen3 (0.6B/4B/8B) to answer typed yes/no, choice, and score questions over a document in one causal prefill pass, returning calibrated probabilities rather than text. Ships a FastAPI /v1/systemone server, frozen eval suites, and a Next.js playground.

AI Frameworks | Python · decision-model · calibration