---
library_name: transformers
tags: [model-merging, mergeability, training-free, quotient-merge-distance]
---

# pythia-en-zh-14m

Training-free merged checkpoint from the **Mergeability** sweep
(`benchmark/emit_lm.py --real`), produced by weight-space merging of two independently
trained parents. No gradient steps were taken.

| field | value |
|---|---|
| pair_id | `pythia-en-zh-14m` |
| merges_in_repo | `average__aligned, average__naive, task_arithmetic__aligned, task_arithmetic__naive, ties__aligned, ties__naive` |
| note | `card backfilled by mergeschool.tools.org_tidy` |

## How it was made

Parents were loaded, activations extracted on a shared calibration corpus, and the merge applied
either **naive** (parents combined in their own coordinates) or **aligned** (parent B carried into
parent A's residual-stream basis via `common.alignment.residual_basis_map` before merging —
permutation for same-width pairs, orthogonal/rectangular for cross-width).

`MS` is the recovery score from `common.eval.mergeability_score` (merged vs. floor vs. ceiling), the
same normalisation used by Zhou et al., so it is comparable across rows of the sweep.

## Caveats

Sub-1B merges are noisy; an aligned signal where the naive one is noise is the finding, not a bug.
Rows without a joint ceiling are floor-relative and must not be read as absolute recovery.

Generated automatically — see the [mergeschool repo](https://github.com/suchirsalhan/merge-school).