fix

modeling_gptbert.py

@@ -327,7 +327,7 @@ class SelfAttention(nn.Module):
 
         self.dropout = nn.Dropout(config.hidden_dropout)
 
-        theta = 160_000 if (layer_idx + 1) % config.short_long_ratio == 0 else 10_000
+        theta = 160_000 if (layer_idx + 1) % config.local_global_ratio == 0 else 10_000
 
         # Initialize rotary embeddings based on whether FlashAttention is available
         if is_flash_attn_2_available():
@@ -515,7 +515,7 @@ class Encoder(nn.Module):
     def __init__(self, config: GptBertConfig):
         super().__init__()
         self.layers = nn.ModuleList([Layer(config, i) for i in range(config.num_layers)])
-        self.short_long_ratio = config.short_long_ratio
+        self.local_global_ratio = config.local_global_ratio
 
     def set_window_length(self, config: GptBertConfig):
         for i, layer in enumerate(self.layers):