Downloads · 30 days
0
bind1-babylm2026-ablations
SecludedCorner/bind1-babylm2026-ablations
bind1-babylm2026-ablations is a text generation model from SecludedCorner. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-4.0.
Companion repo to the entry SecludedCorner/bind1-babylm2026-strict-small: every retrained ablation family behind the papers' claims, as loadable checkpoints (one branch each, trustremotecode). Eval-time ablations (sev…
Access
Public
Updated Jul 8, 2026
Repo size
1.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.md2.3 KB · 60%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- cc-by-4.0
- Access
- Public
- Created
- Jul 8, 2026
- Updated
- Jul 8, 2026
- SHA
- 927fe702
Try a prompt
Model card
From the Hugging Face model README
bind1 — trained-ablation checkpoints (BabyLM 2026 Strict-Small)
Companion repo to the entry
SecludedCorner/bind1-babylm2026-strict-small:
every retrained ablation family behind the papers' claims, as loadable checkpoints
(one branch each, trust_remote_code). Eval-time ablations (severed edge, forced-$T$) need no
weights of their own — they are config-only clones of the entry; scripts in the
code repo.
Branches
| Branch | What it is | Headline number |
|---|---|---|
tt1_seed0 … tt1_seed9 | identical architecture trained single-pass ($T{=}1$), ten seeds | entity tracking never forms: 17.4±2.4 (chance ≈ 20.0) in 10/10, grammar healthy (BLiMP 65.4±0.9) — training-time iteration is the scaffold |
novg_seed0 … novg_seed3 | trained with the verdict-to-trust edge frozen at zero, four seeds | single-pass write fails to form in 3/4 (19–30) and formed anyway in one (39.7) — the edge raises the odds, not strictly necessary |
Loading any branch:
model = AutoModelForCausalLM.from_pretrained(
"SecludedCorner/bind1-babylm2026-ablations", revision="tt1_seed0", trust_remote_code=True)
Per-item evaluation outputs for all of these live in the
eval-artifacts dataset.
Internal ids: tt1_seedN = bind1_tt1_sN; novg_seedN = bind1_tt3_sN_novg
(physical loop2_novg(_sN)).
Honest note
These are the ablations that disagreed with us as often as they agreed: the ten-seed test falsified the "single-pass training might suffice" reading, and seed 3 of the frozen-edge family falsified "the edge is strictly necessary." Released so the disagreements are verifiable too.
Citation
Yulin Yang (ORCID 0009-0007-4827-8449). A Microkernel Language Model: Reasoning as Mutually-Supporting Aggregates, and Why Its Parts Must Be Judged Together. BabyLM Challenge 2026 (Strict-Small track) submission.
- Task
- Text Generation
- Library
- transformers
- License
- cc-by-4.0
- Languages
- en
- Created
- Jul 8, 2026
- Updated
- Jul 8, 2026