zils-mini-nx1
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: the start is the uniform weight average of the three bodies of the 14 November 2026 d3-mini soup (Zayaan/zils-mini-hm4, qhoenix/zils-mini-decision-t2avg, joamCriff123/zils-mini-m1113b), all Apache-2.0; credit for the start belongs to their authors and to the authors of the bodies they were built from. The body is one rank-64 LoRA run (lr 5e-5, one epoch) on the training data below, merged into the start.
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 dataset rows: train-side splits for the known task families; for the new-domain style tasks, rows of the public new-domain task pools listed in scripts/author_exam.py (BIG-bench task files and splits of other public datasets, mostly held-out validation/test splits; BIG-bench tasks used by the public seed exams were excluded), plus the public Zils relay teacher answers. No validator exam items, no public seed exam items and no customer data were used. This repository holds weights only; check the source datasets' terms before reuse.