Instructions to use posie/bert-base-chinese-accidentreason-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use posie/bert-base-chinese-accidentreason-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="posie/bert-base-chinese-accidentreason-classifier")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("posie/bert-base-chinese-accidentreason-classifier") model = AutoModelForMaskedLM.from_pretrained("posie/bert-base-chinese-accidentreason-classifier") - Notebooks
- Google Colab
- Kaggle
这个模型适用于处理中文原因文本,并标记文本中的不安全行为或影响因素
需要注意的是,本模型将不安全行为与影响因素的多标签标记任务视作相互独立的二分类任务,模型最后一层使用了sigmoid函数,但是在本api测试中,对模型的输出结果作了一层softmax
本模型是在文本对应位置标签的概率计算如果大于0.5,认为文本含有该标签信息的基础上进行的训练
- Downloads last month
- 4