zils-mini-nt2
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 the uniform average of two rank-64 LoRA runs (lr 5e-5, one epoch, different seeds) on the training data below, each merged into the start.
Training data: 63,840 typed decisions from the train split of tasksource/tasksource-jev-typed-decisions (only rows marked license_use: commercial, mostly-ASCII text, at most 200 rows per source dataset, 413 sources), converted to the Zils training format; each row keeps its source's licence, see that dataset's card. 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.