zl-mini-o2
A d3-mini soup body for Zils (Bittensor subnet 127).
- Start: the current official d3-mini soup (round d3-mini-2026-11-12, soup sha256 9a21f188โฆ), rebuilt with
zils.soup.buildfromqhoenix/zils-mini-decision-l13_avg678@ 091c6eb andjoamCriff123/zils-mini-sx3@ c9432ad. - Training: LoRA rank 32, lr 4e-5, one epoch, soft cross-entropy plus Brier loss with a KL anchor (0.3) to the start.
- Data: about 15,900 exam-format items. About 9,800 are resolved real-world outcomes collected with
zils.currentfrom open CC0 / CC-BY-SA sources (Wikipedia and Wikidata edit reverts, AfD and AfC outcomes, arXiv categories), labelled by what actually happened. The rest are program-verified arithmetic items (questions seeded from the GSM8K train split, written by gpt-oss-20b, labels computed by executing code) and earlier items for the other known families written by open-weight models. Items were deduplicated against held-out evaluation data by source row, normalized fingerprints, option order and embedding similarity.
Weights are bf16 safetensors in the pool's layout. License: Apache-2.0, as its parents.
- Downloads last month
- 26
Model tree for jwcwn/zl-mini-body-5
Base model
joamCriff123/zils-mini-sx3