zils-mini-p16

A body for the Zils d3-mini soup pool (Bittensor subnet 127): a fine-tune of Qwen/Qwen3.5-4B in the chassis layout, BF16, language weights trained, vision tower from the parent.

Soup fine-tune of the 11 November mini soup: uniform average of 16 independently trained members (full fine-tunes of the upper half at lr 1.5e-6 and 3e-6, rank-32 and rank-64 anchored LoRAs), no extrapolation.

Training data: exam-format decision items written with the public Zils authoring recipe (scripts/author_exam.py) by Claude Opus and by a local open model, from public training splits only, plus the public Zils relay teacher answers. No validator exam items and no public seed items were used. This repository holds weights only; check the source datasets' terms before reuse.