zoo-mono_vs_joint-beetle-monolingual-humanscale-zho__beetle-bilingual-l2-50-sequential-e970e3b7

zoo-mono_vs_joint-beetle-monolingual-humanscale-zho + beetle-bilingual-l2-50-sequential-e970e3b7

Merged checkpoints for one model pair. 1 variant(s) in this repository: qmd_guided__transport.

• Operators present: qmd_guided
• Arms present: transport

What this is

A model-merging artefact, not a model anyone should deploy. Each folder is one merge of two parent models, published so that the merging results in the accompanying work are inspectable and reproducible rather than taken on trust.

Folders are named <recipe>__<arm>:

Regime warning, which matters more than usual here

These are sub-1B models pretrained from scratch, not fine-tunes of a shared checkpoint. In this regime merging is destructive: across 2,320 merges the mean change in NLL against the better parent is about -1.4 nats, and a merge that beats its better parent is rare. That is a finding, not a defect of these artefacts, and it is the opposite of what the model-soup literature reports for the regime it studies. Both can be true; the regimes differ. Do not read a merge here as a capable model.

Provenance of the numbers

Merge quality for every artefact in this org is recorded in the accompanying repository's sweep tables, with delta_floor (nats against the better parent) as the outcome. Alignment-dependent columns from sweeps predating the fix are void; see the note above where it applies.