Skip to content

Commit

Permalink
Pass use_cache in kwargs for GPTNeoX (#30538)
Browse files Browse the repository at this point in the history
pass use_cache in kwargs
  • Loading branch information
zucchini-nlp authored and Ita Zaporozhets committed May 14, 2024
1 parent 2782292 commit e52ffbe
Showing 1 changed file with 1 addition and 0 deletions.
1 change: 1 addition & 0 deletions src/transformers/models/gpt_neox/modeling_gpt_neox.py
Original file line number Diff line number Diff line change
Expand Up @@ -1108,6 +1108,7 @@ def prepare_inputs_for_generation(
"attention_mask": attention_mask,
"past_key_values": past_key_values,
"position_ids": position_ids,
"use_cache": kwargs.get("use_cache"),
}
)

Expand Down

0 comments on commit e52ffbe

Please sign in to comment.