Results 8 issues of NLP

您好! 请问您们是按照什么样的策略将知识图谱的数据集划分成训练集、测试集的?能否告知呢?

感覺復現的有問題。原始數據acc無任何變動呀

使用deepspeed 多机分布式训练,加载opt-1.3b 模型的时候,报a leaf Variable that requires grad is being used in an in-place operation错误

如题?如何将130B的FasterTransformer适配到chatglm-6b呢?

### Is there an existing issue for this? - [X] I have searched the existing issues ### What is your question? 我将VARCHAR 的最大长度设置为200,然后,我在存入数据的时候,使用100去过滤文本长度,最后还是报文本长度有237,超出最大长度限制。我想请问,milvus计算文本的逻辑是什么呢?是按照什么去计算文本的长度的呢? ### Anything else? _No response_

kind/question

我看新分支里面的,一个instance一个关系,如何做到识别一个instance里面有多个关系呢? 如果一个instance里面,有多个不同实体对,是相同关系的如何构建输入的instance呢

No module named "RelationExtractionWithNERReader" and "NERReader", could you provide the complete code?

I have read this article, but I did not find any introduction on how to generate a template!could you please tell me how to generate a template?