Invoke the out_balancer of attention_squeeze
This commit is contained in:
parent
0522425ea8
commit
b5e0676f14
@ -1445,6 +1445,7 @@ attn_weights: a Tensor of shape (num_heads, batch_size, seq_len, seq_len)
|
||||
x = x * scales
|
||||
x = self.activation(x) # Identity only. For diagnostics.
|
||||
x = self.out_proj(x)
|
||||
x = self.out_balancer(x)
|
||||
return x
|
||||
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user