BERTc-165M-MT

BERTc-165M-MT is a Chinese multi-task tagging model fine-tuned from Ismantic/BERTc-165M. It predicts:

• CWS: Chinese word segmentation
• POS: PD-1998 POS tags mapped to the LTP tag set
• NER: Nh / Ns / Ni entity spans in BIES format

Metrics

PD-1998 dev joint score:

• Joint score: 1.4689
• CWS micro F1: 0.9836
• POS per-word acc: 0.9753
• NER micro F1: 0.9632

Training recipe:

• backbone: Ismantic/BERTc-165M
• epochs: 5
• batch size: 64
• learning rate: bert_lr=2e-5, head_lr=5e-4
• warmup ratio: 0.1
• FGM: enabled, eps=1.0
• loss weights: alpha_pos=2.0, beta_ner=0.5

Files

• model.safetensors: MT state dict for the backbone and task heads.
• config.json: BERTc backbone architecture.
• model.py: Modern BERTc implementation.
• mt_model.py: MT wrapper, tokenizer adapter, and decode helpers.
• piece.model: tokenizer model; load with piece_tokenizer using cn_dict="no".
• mask_token_id.txt: mask token id used by the backbone tokenizer.
• mt_config.json: task metadata and source checkpoint.

Usage

from mt_model import BERTcForMT, PieceCharTokenizer

tok = PieceCharTokenizer(".")
model = BERTcForMT.from_pretrained(".")
out = model.predict("中华人民共和国万岁", tok)
print(out["words"])
print(out["pos"])
print(out["ner"])