zils-lite-lxh3
A body for the Zils d3-lite soup pool (Bittensor subnet 127): a fine-tune of Qwen/Qwen3.5-0.8B 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 two bodies of the 14 November 2026 d3-lite soup (VadymPikulyk/zils-lite-dh2 and qhoenix/zils-lite-decision-avg-abc), both 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 three rank-64 LoRA runs (lr 1e-4, one epoch each, different seeds) on the training data below, each 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). 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.