Structured Direct-Sum study
Collection
Controlled Strict-Small study of syntax, lexical, and conceptual priors. • 13 items • Updated
How to use miguelcsx/tolm-structured-ds-dense with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("fill-mask", model="miguelcsx/tolm-structured-ds-dense", trust_remote_code=True) # Load model directly
from transformers import AutoModelForMaskedLM
model = AutoModelForMaskedLM.from_pretrained("miguelcsx/tolm-structured-ds-dense", trust_remote_code=True, device_map="auto")This repository preserves an already-trained checkpoint from the controlled BabyLM research tournament. No training or evaluation was run for this release.
main is identical to chck_100M, selected from the existing local tournament
record. Other revisions, when present, are archived checkpoints rather than new
experiments.
| Evaluation | Score |
|---|---|
| BLiMP | 67.96 |
| Supp | 63.60 |
| EWoK | 50.00 |
| ET | 22.13 |
| COMPS | 51.96 |
| GlobalPIQA | 40.10 |
The canonical code is maintained at
miguelcsx/tolm. Remote code is required to
load this custom Transformers model; review tolm.py before use.