hhhhnwl

尝试了一下mnext.py中注视掉的expansion ratio基本都是4的这个结构: #self.cfgs = [ # # t, c, n, s # [1, 16, 1, 1], # [4, 24, 2, 2], # [4, 32, 3, 2], # [4, 64, 3,...

In Base Module and Temporal Evaluation Module,all of the conv1d layer group=4,but I haven't say the param in paper.

question about penalty

4

`prior = torch.ones(args.num_class)/args.num_class` `prior = prior.cuda()` `pred_mean = torch.softmax(logits, dim=1).mean(0)` `penalty = torch.sum(prior*torch.log(prior/pred_mean))` entropy=p*log(p) why not penalty = `torch.sum(pred_mean*torch.log(prior/pred_mean))`

### Is there an existing issue for this? - [x] I have searched the existing issues ### Current Behavior Traceback (most recent call last): File "/mnt/g/work/gpt/chatglm_new/ChatGLM-6B/ptuning/main.py", line 432, in main()...