Downloads · 30 days
3
60% of all-time downloads
goldfish-en-pol_latn
Mergeability/goldfish-en-pol_latn
goldfish-en-pol_latn is a machine learning model from Mergeability. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Training-free merged checkpoint from the Mergeability sweep (benchmark/emitlm.py --real), produced by weight-space merging of two independently trained parents. No gradient steps were taken.
All-time downloads
5
Public
Repo size
8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors12 GB · 99%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Aug 8, 2026
- Updated
- Aug 16, 2026
- SHA
- 46c1d485
Model card
From the Hugging Face model README
goldfish-en-pol_latn
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 | goldfish-en-pol_latn |
| merges_in_repo | average__aligned, average__naive, average__transport, csp__aligned, csp__naive, csp__transport, dare__aligned, dare__naive, dare__transport, opcm__aligned, opcm__naive, opcm__transport, ortho_merge__aligned, ortho_merge__naive, ortho_merge__transport, svc__aligned, svc__naive, svc__transport, task_arithmetic__aligned, task_arithmetic__naive, task_arithmetic__transport, ties__aligned, ties__naive, ties__transport |
| 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.
- Library
- transformers
- Created
- Aug 8, 2026
- Updated
- Aug 16, 2026