Downloads · 30 days
9
0% of all-time downloads
LikC1606/chinesebabylm-treatment-nfkc-bert-mlm-4p66m
chinesebabylm-treatment-nfkc-bert-mlm-4p66m is a fill-mask model from LikC1606. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as other.
Small from-scratch BERT-style masked language model trained as the Round 20 DeepScientist NFKC-normalization treatment pilot.
Downloads · 30 days
9
0% of all-time downloads
All-time downloads
3K
Public
Parameters
4.7M
18.6 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors18.6 MB · 99%
From the Hugging Face model README
Small from-scratch BERT-style masked language model trained as the Round 20 DeepScientist NFKC-normalization treatment pilot.
BertForMaskedLMChinese BabyLM official 10k stratified sample with NFKC text normalization.
Official zero-shot evaluator results:
| Task | Accuracy |
|---|---|
| ZhoBLiMP | 53.53 |
| Hanzi structure | 58.00 |
| Hanzi pinyin | 74.00 |
| Mean available tasks | 61.84 |
This model was packaged from treatment_round20_nfkc_bert_mlm_4p66m in the local ChineseBabyLM best-model archive.