ZX-lang
Results
2
comments of
ZX-lang
> So, what's the URL you access to? we try to use 127.0.0.1 or the real ip of my comupter such as 192.168.1.103,but none of them can reach the login...
> https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/BGE_M3/modeling.py#L302 交叉熵损失，对pos和neg计算分数，将正样本作为正确分类计算损失 我debug了一下代码，请问可以这么理解么，计算query和所有passage的分数，然后选取最大分数的那个passage下标作为预测值，实际pos的位置为label，然后计算交叉熵损失