Loading profile…
ORGANIZATION
@mathias-strasser
Independent developer of Jeff, a small open decision model with per-task LoRA adapters (GitHub firelex, Hugging Face mstrasser). A personal project, not a company.
A 0.8B fine-tune of Qwen3.5-0.8B that returns a calibrated probability for each listed option in one forward pass (choice, yes/no, score), through a trained readout head. v1.3 is adapter-first, with 15 per-task LoRA adapters; for zero-shot use the maker points to v1.2.
78.6%26.6 ms800Mapache-2.0
