bugfix memory leak

Author: LauraGPT

model.py

@@ -190,13 +190,13 @@ def forward_attention(self, value, scores, mask, mask_att_chunk_encoder=None):
                 "inf"
             )  # float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
             scores = scores.masked_fill(mask, min_value)
-            self.attn = torch.softmax(scores, dim=-1).masked_fill(
+            attn = torch.softmax(scores, dim=-1).masked_fill(
                 mask, 0.0
             )  # (batch, head, time1, time2)
         else:
-            self.attn = torch.softmax(scores, dim=-1)  # (batch, head, time1, time2)
+            attn = torch.softmax(scores, dim=-1)  # (batch, head, time1, time2)
 
-        p_attn = self.dropout(self.attn)
+        p_attn = self.dropout(attn)
         x = torch.matmul(p_attn, value)  # (batch, head, time1, d_k)
         x = (
             x.transpose(1, 2).contiguous().view(n_batch, -1, self.h * self.d_k)