Wanqing Cui

Results 3 comments of Wanqing Cui

Hello, I met the same problem. Have you solved this problem and how to run it? Thanks.

Upon further analysis, I discovered significant differences in embedding values at non-padding positions across different batch sizes. This discrepancy appears to correlate with the observed instability in results. For example:...

您好,您的邮件我已经收到,我会第一时间处理。