[BUG] Dimension errors in RGLRU class

[MisakiWho]

[Description]

In forward() of class RGLRU, the dimension of x is [Batch_size, dim],
but the dimension of self.Wa is [hidden_dim,dim],
where hidden_dim=mul*dim, how could RGLRU work?

"linear_1 = self.lru(linear_1)"
This line is commented in the code.

Upvote & Fund

• We're using Polar.sh so you can upvote and help fund this issue.
• We receive the funding once the issue is completed & confirmed by you.
• Thank you in advance for helping prioritize & fund our backlog.

[github-actions]

Hello there, thank you for opening an Issue ! 🙏🏻 The team was notified and they will get back to you asap.

[github-actions]

Stale issue message