Downloads · 30 days
4
19% of all-time downloads
Entro-changyu/Taiwanese-mBERT
Taiwanese-mBERT is a machine learning model from Entro-changyu. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
本模型以 mBERT(bert-base-multilingual-cased)為基礎,進行全參數微調,應用於台語健康照護文本的身體部位詞辨識任務。此任務採用字元級序列標註(character-based sequence labeling)架構。
Downloads · 30 days
4
19% of all-time downloads
All-time downloads
21
Public
Parameters
177M
709 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors709 MB · 99%
From the Hugging Face model README
本模型以 mBERT(bert-base-multilingual-cased)為基礎,進行全參數微調,應用於台語健康照護文本的身體部位詞辨識任務。此任務採用字元級序列標註(character-based sequence labeling)架構。
bert-base-multilingual-casedO, B-BODY, I-BODY(BIO 編碼)from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("Entro-changyu/Taiwanese-mBERT")
model = AutoModelForTokenClassification.from_pretrained("Entro-changyu/Taiwanese-mBERT")
inputs = tokenizer("頭殼痛欲食藥", return_tensors="pt", is_split_into_words=False)
outputs = model(**inputs)
| 標籤 | 說明 |
|---|---|
O | 非身體詞 |
B-BODY | 身體部位詞開頭 |
I-BODY | 身體部位詞內部 |
本模型僅供學術研究與教學用途。其訓練語料來源非臨床記錄,模型亦未經臨床驗證,請勿用於真實醫療決策或診斷情境。
若您在使用上有任何建議、錯誤回報或貢獻意願,歡迎透過 Hugging Face 與我聯絡!