Downloads · 30 days
30
38% of all-time downloads
mrmikat/lilliput-curriculum-rtd
lilliput-curriculum-rtd is a fill-mask model from mrmikat. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
A 31M-parameter DeBERTa-v2 masked language model trained from scratch for the BabyLM 2026 Strict-Small track.
Downloads · 30 days
30
38% of all-time downloads
All-time downloads
78
Public
Parameters
31.2M
2.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors125 MB · 99%
From the Hugging Face model README
A 31M-parameter DeBERTa-v2 masked language model trained from scratch for the BabyLM 2026 Strict-Small track.
from transformers import AutoModelForMaskedLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("mrmikat/lilliput-curriculum-rtd")
model = AutoModelForMaskedLM.from_pretrained("mrmikat/lilliput-curriculum-rtd")