---
library_name: transformers
tags:
- model-merging
- mergeability
- research-artifact
- do-not-use-aligned-variant
---

# polypythia-14m-s1s2

Merged checkpoints for one model pair. **6 variant(s)** in this repository: `average__aligned`, `average__naive`, `task_arithmetic__aligned`, `task_arithmetic__naive`, `ties__aligned`, `ties__naive`.

- Operators present: `average`, `task_arithmetic`, `ties`
- Arms present: `aligned`, `naive`

## ⚠️ The `__aligned` variants in this repository are not usable

They were merged from models damaged by a bug in our alignment code. The role table that classifies a
parameter by its relation to the residual stream did not recognise this architecture's tensor names,
so **90.8% of the residual-facing parameter mass was left unpermuted** while attention and both norm
tensors were permuted. The result is not an aligned model; it is a broken one. Under a map that must
be exactly function-preserving, the logits moved by a relative 0.32 (it must be ~1e-7).

**Do not use, cite, or benchmark against the `__aligned` folders here.** The `__naive` and
`__transport` folders are unaffected and remain valid: the bug only ever touched the aligned arm.

The bug is fixed (`common/alignment.py` now classifies these names, `residual_coverage()` reports the
fraction classified, and `align_state_dict(..., strict=True)` raises rather than silently skipping
tensors when it cannot classify ≥99% of the residual-facing mass). Corrected aligned merges are being
regenerated from the re-run sweep.


## 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>`:

| part | meaning |
|---|---|
| `average`, `task_arithmetic`, `ties`, `qmd_guided` | the merge operator |
| `__naive` | parents merged as-is |
| `__aligned` | parents merged after a function-preserving alignment map |
| `__transport` | parents merged after vocabulary transport (cross-tokenizer pairs) |

## 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.