body

README.md

@@ -0,0 +1,20 @@
+---
+license: apache-2.0
+base_model:
+- Qwen/Qwen3.5-4B
+- perplexity-ai/pplx-decider-flash-v1.2
+- Maincode/Matilda-Decision-v1-Mini
+- PelaAI/KnowLine-4B-Gen5
+tags:
+- zils
+- decision-model
+- soup-body
+---
+
+# zils-mini-hp7
+
+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.
+
+House-lineage body: start = average of three house models; 7 independently trained members (upper-half full fine-tunes and anchored LoRAs) averaged, x1.3 from 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 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.

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6b631123a4e83ce8c8e78c9709a51c2de8f8927fc9ae66dbb6db9d139cd0d2
+size 9078616200

zils-owner.json

@@ -0,0 +1 @@
+{"hotkey": "5FBntQs4VVZahRJDHh98YpfxNKJp9AYdyyGBjEeWx7dCxyDT"}