PRISM D384 controlled study
Collection
Two-seed controlled PRISM study: frozen-state and RTD ablations. • 11 items • Updated
How to use miguelcsx/prism-control with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("fill-mask", model="miguelcsx/prism-control", trust_remote_code=True) # Load model directly
from transformers import AutoModelForMaskedLM
model = AutoModelForMaskedLM.from_pretrained("miguelcsx/prism-control", 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 | 67.75 |
| Supp | 60.80 |
| EWoK | 48.09 |
| ET | 23.95 |
| COMPS | 52.22 |
| GlobalPIQA | 32.18 |
The canonical code is maintained at
miguelcsx/tolm. Remote code is required to
load this custom Transformers model; review tolm.py before use.