Add sliding window and optimize redundant code (#2655)

Author: Ace-To-HYB

paddleformers/transformers/configuration_utils.py

@@ -1269,3 +1269,20 @@ def get_configuration_file(configuration_files: List[str]) -> str:
             break
 
     return configuration_file
+
+
+ALLOWED_LAYER_TYPES = (
+    "full_attention",
+    "sliding_attention",
+)
+
+
+def layer_type_validation(layer_types: List[str], num_hidden_layers: Optional[int] = None):
+    """Check that `layer_types` is correctly defined."""
+    if not all(layer_type in ALLOWED_LAYER_TYPES for layer_type in layer_types):
+        raise ValueError(f"The `layer_types` entries must be in {ALLOWED_LAYER_TYPES}")
+    if num_hidden_layers is not None and num_hidden_layers != len(layer_types):
+        raise ValueError(
+            f"`num_hidden_layers` ({num_hidden_layers}) must be equal to the number of layer types "
+            f"({len(layer_types)})"
+        )

paddleformers/transformers/qwen2/configuration.py

@@ -14,7 +14,7 @@
 # limitations under the License.
 """Qwen2 model configuration"""
 
-from ..configuration_utils import PretrainedConfig
+from ..configuration_utils import PretrainedConfig, layer_type_validation
 
 __all__ = [
     "Qwen2Config",
@@ -129,6 +129,7 @@ def __init__(
         attention_dropout=0.0,
         rope_scaling_factor=1.0,
         rope_scaling_type=None,
+        layer_types=None,
         pp_seg_method="layer:Qwen2DecoderLayer",
         **kwargs,
     ):
@@ -167,6 +168,14 @@ def __init__(
 
         self.pp_seg_method = pp_seg_method
 
+        self.layer_types = layer_types
+        if self.layer_types is None:
+            self.layer_types = [
+                "sliding_attention" if self.use_sliding_window and i >= self.max_window_layers else "full_attention"
+                for i in range(self.num_hidden_layers)
+            ]
+        layer_type_validation(self.layer_types, self.num_hidden_layers)
+
         super().__init__(
             pad_token_id=pad_token_id,
             bos_token_id=bos_token_id,
@@ -190,5 +199,6 @@ def __init__(
                 "pp_seg_method",
                 "dpo_config",
                 "kto_config",
+                "layer_types",
             ]
         )