Fix Switch Transformers When sparse_step = 1 (#28564)

Fix sparse_step = 1

I case sparse_step = 1, the current code will not work.

src/transformers/models/switch_transformers/modeling_switch_transformers.py

@@ -898,7 +898,7 @@ class SwitchTransformersStack(SwitchTransformersPreTrainedModel):
         config.num_layers = config.num_decoder_layers if self.is_decoder else config.num_layers
         self.block = nn.ModuleList()
         for i in range(config.num_layers):
-            is_sparse = (i % sparse_step == 1) if sparse_step > 0 else False
+            is_sparse = (i % sparse_step == 1 or sparse_step == 1) if sparse_step > 0 else False
 
             self.block.append(
                 SwitchTransformersBlock(config, has_relative_attention_bias=bool(i == 0), is_sparse=is_sparse)