ChineseBabyLM Control AdamW BERT MLM 9.53M

Small from-scratch BERT-style masked language model trained as the Round 20 DeepScientist control-arm AdamW no-bias-correction pilot.

Model Details

  • Architecture: BertForMaskedLM
  • Model type: masked language model / encoder-only BERT
  • Parameters: 9,527,714
  • Layers: 4
  • Attention heads: 6
  • Hidden size: 384
  • Vocabulary size: 5,666
  • Max position embeddings: 256

Training Data

Chinese BabyLM official 10k stratified sample; control-arm Round 20 AdamW no-bias-correction pilot.

Evaluation

Official zero-shot evaluator results:

Task Accuracy
ZhoBLiMP 59.74
Hanzi structure 47.00
Hanzi pinyin 31.00
Mean available tasks 45.91

Package Source

This model was packaged from control_round20_adamw_no_bias_correction_bert_mlm_9p53m in the local ChineseBabyLM best-model archive.

Downloads last month
5
Safetensors
Model size
9.53M params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support