提交 f85f9cb4 编写于 作者: Stevezhangz's avatar Stevezhangz

Update README.md

上级 33ca3759
# BERT-pytorch
Repeted by pytorch, without pre-train.
Now, could be trained by mask word2idx.
And, I am foucsing on the conversation training.
Introduction:
This mechine could be trained by "train_demo.py"
And there are mainly two datasets demo, one is a json file about poem, another is a conversation demo created by myself.
However I don't recommand to use those demo_datas to train, I prefer use formal datasets.
Funtune method could be found in "Bert_finetune.py", funtune examples mainly include two.
First is the word classify prediction, could be found in ["bert_for_word_classify.py"]{https://codechina.csdn.net/captainAAAjohn/BERT-pytorch/-/blob/main/bert_for_word_classify.py}
Second is the sentences classify prediction, could be found in [" bert_for_sentence_classify.py"]{https://codechina.csdn.net/captainAAAjohn/BERT-pytorch/-/blob/main/bert_for_sentence_classify.py}
Next, I will enrich the language generation as well as conversation process.
# How to use
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册