fix

modeling_gptbert.py

@@ -260,7 +260,7 @@ def apply_rotary_unpadded(qkv, cos, sin, cu_seqlens: Optional[torch.Tensor] = No
 # from https://github.com/huggingface/transformers/blob/main/src/transformers/models/modernbert/modeling_modernbert.py
 class UnpaddedRotaryEmbedding(RotaryEmbedding):
     def __init__(self, dim: int, base: float = 10000.0, max_seqlen: Optional[int] = None):
-        super().__init__(dim=dim, base=base, pos_idx_in_fp32=True, device=None, interleaved=False)
+        super().__init__(dim=dim, base=base, device=None, interleaved=False)
         self.max_seqlen = max_seqlen
 
     def forward(self, qkv: torch.Tensor, cu_seqlens: torch.Tensor, max_seqlen: Optional[int] = None) -> Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]: