SikuBERT-verb-wuyan-couplet-simplified-0.1

This is a fine-tuned SikuBERT model for token-level verb classification in Classical Chinese couplets.
It classifies each character as either verb or non-verb.

---

Usage

from transformers import pipeline

classifier = pipeline(
    "token-classification",
    model="qhchina/SikuBERT-verb-wuyan-couplet-simplified-0.1",
)

text = "玉叶依岩聚，金枝触石分"
outputs = classifier(text)

for token in outputs:
    label = 1 if token["entity"] == "verb" else 0
    print(f"{token['word']} -> {label}")

# 玉 -> 0
# 叶 -> 0
# 依 -> 1
# 岩 -> 0
# 聚 -> 1
# ， -> 0
# 金 -> 0
# 枝 -> 0
# 触 -> 1
# 石 -> 0
# 分 -> 1