We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 625f510 commit cf8aedfCopy full SHA for cf8aedf
keras_hub/src/models/qwen3/qwen3_attention.py
@@ -299,7 +299,7 @@ def _compute_attention(
299
attention_scores,
300
ops.cast(self._inv_norm_factor, self.compute_dtype),
301
)
302
- if not self.sliding_window_size:
+ if self.sliding_window_size:
303
attention_mask = self._mask_sliding_window(
304
attention_mask,
305
cache_update_index=cache_update_index
0 commit comments