Unverified Commit 762dda44 authored by Matthew McDermott's avatar Matthew McDermott Committed by GitHub
Browse files

Remove extra "`max_length` is reached." from InfNaNLogitsProcessor documentation (#21634)

* Fix typo in documentation.

* Remove trailing words typo in documentation.
parent 26ef0f19
......@@ -805,8 +805,7 @@ class ForcedEOSTokenLogitsProcessor(LogitsProcessor):
class InfNanRemoveLogitsProcessor(LogitsProcessor):
r"""
[`LogitsProcessor`] that removes all `nan` and `inf` values to avoid the generation method to fail. Note that using
the logits processor should only be used if necessary since it can slow down the generation method. `max_length` is
reached.
the logits processor should only be used if necessary since it can slow down the generation method.
"""
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment