Update configuration_longcat_flash.py (#5)

- Update configuration_longcat_flash.py (4357d408aa0bfbac7d38b5cea2bda88745a338b5)


Co-authored-by: WangJianing <[email protected]>

configuration_longcat_flash.py

@@ -1,4 +1,3 @@
-
 """LongcatFlash model configuration"""
 
 from transformers.configuration_utils import PretrainedConfig
@@ -53,7 +52,7 @@ class LongcatFlashConfig(PretrainedConfig):
             Dimension of the value heads.
         qk_nope_head_dim (`int`, *optional*, defaults to 128):
             Dimension of the query/key heads that don't use rotary position embeddings.
-        norm_topk_prob (`bool`, *optional*, defaults to `True`):
+        norm_topk_prob (`bool`, *optional*, defaults to `False`):
             Whether to normalize the weights of the routed experts.
         hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
             The non-linear activation function (function or string) in the decoder.
@@ -213,4 +212,4 @@ class LongcatFlashConfig(PretrainedConfig):
         return self.num_layers
 
 
-__all__ = ["LongcatFlashConfig"]
+__all__ = ["LongcatFlashConfig"]