Core: Fix copies on main (huggingface#29624)

fix fix copies

src/transformers/models/gptj/modeling_gptj.py

@@ -454,7 +454,7 @@ def _flash_attention_forward(
             attention_mask (`torch.Tensor`):
                 The padding mask - corresponds to a tensor of size `(batch_size, seq_len)` where 0 stands for the
                 position of padding tokens and 1 for the position of non-padding tokens.
-            dropout (`int`, *optional*):
+            dropout (`float`):
                 Attention dropout
             softmax_scale (`float`, *optional*):
                 The scaling of QK^T before applying softmax. Default to 1 / sqrt(head_dim)