Update AlphaS2S.py

AlphaS2S.py

@@ -196,7 +196,7 @@ class EncoderBlock(layers.Layer):
     def __init__(self, d_model, num_heads, dff, dropout=0.1):
         super().__init__()
         self.mha = layers.MultiHeadAttention(num_heads=num_heads, key_dim=d_model)
-        self.ffn = SwiGLU(d_model, 512)
+        self.ffn = SwiGLU(d_model, 320)
         self.norm1 = layers.LayerNormalization(epsilon=1e-6)
         self.norm2 = layers.LayerNormalization(epsilon=1e-6)
         self.dropout1 = layers.Dropout(dropout)
@@ -222,7 +222,7 @@ class LoU(layers.Layer):
         self.alpha_linear = layers.Dense(1, activation='sigmoid', dtype='float32')
 
         self.cross = CrossBlock()
-        self.glu = SwiGLU(d_model, 512)
+        self.glu = SwiGLU(d_model, 320)
 
     def _ema_over_time(self, score, alpha_dynamic):
         seq = tf.transpose(score, perm=[1, 0, 2])