Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于预训练模型 #1

Open
nieallen opened this issue Mar 4, 2022 · 6 comments
Open

关于预训练模型 #1

nieallen opened this issue Mar 4, 2022 · 6 comments

Comments

@nieallen
Copy link

nieallen commented Mar 4, 2022

您好,SentiLARE_pretrain_roberta是放的roberta-base模型吗?是需要.bin文件,config.json,vocab.txt吗?

@lshowway
Copy link
Owner

lshowway commented Mar 8, 2022

@nieallen 抱歉刚看到,不知道为什么没有收到github 提醒。
是roberta-base模型,需要你说的这些文件。直接XXX.from_pretrained("roberta-base"),它会自动下载。你也可以手动从huggingface的archive中下载,然后XXX.from_pretrained(模型目录,是目录不用到.bin文件)

@lshowway
Copy link
Owner

lshowway commented Mar 8, 2022

@nieallen 下载地址是这个:https://huggingface.co/models

@nieallen
Copy link
Author

您好,我用了bert-base-chinese在中文数据集实验的,但是中文没有SWC那样的情感词典,我自己用训练语料做jieba分词后标注了200个情感词,最终准确率只有90%,想知道您有在中文数据集上试过吗

@lshowway
Copy link
Owner

@nieallen I push a new commit, where a previous version paper is added, which includes some experiments on Chinese datasets.

@lshowway
Copy link
Owner

@nieallen It is a long long-ago version, just used to refer to the Chinese sentiment dictionary and results.

@BABBU18
Copy link

BABBU18 commented Feb 22, 2024

请问中文数据集,具体是如何操作的

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants