fix

modeling_gptbert.py

@@ -243,9 +243,6 @@ class UnpaddedRotaryEmbedding(RotaryEmbedding):
         super().__init__(dim=dim, base=base, pos_idx_in_fp32=True, device=None, interleaved=False)
         self.max_seqlen = max_seqlen
 
-        if max_seqlen is not None and device is not None and dtype is not None:
-            self._update_cos_sin_cache(max_seqlen, device=device, dtype=None)
-
     def forward(self, qkv: torch.Tensor, cu_seqlens: torch.Tensor, max_seqlen: Optional[int] = None) -> Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]:
         if max_seqlen is not None:
             self._update_cos_sin_cache(max_seqlen, device=qkv.device, dtype=qkv.dtype)