riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-02 19:21:31 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Fix gradient checkpointing imagegpt (#21816)

Browse Source 
* Fix gradient checkpointing bug in gptneox

* Fix gradient checkpointing bug in modeling_imagegpt.py

* Revert gpt neox changes

---------

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
This commit is contained in:
Karim Foda 2023-02-28 12:47:04 +00:00 committed by GitHub
parent e07a3d95f8
commit 4fe744f528
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/transformers/models/imagegpt/modeling_imagegpt.py
View File

@ -791,6 +791,13 @@ class ImageGPTModel(ImageGPTPreTrainedModel):
output_shape = input_shape + (hidden_states.size(-1),)
if self.gradient_checkpointing and self.training:
if use_cache:
logger.warning_once(
"`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
)
use_cache = False
presents = () if use_cache else None
all_self_attentions = () if output_attentions else None
all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
@ -811,11 +818,6 @@ class ImageGPTModel(ImageGPTPreTrainedModel):
all_hidden_states = all_hidden_states + (hidden_states,)
if self.gradient_checkpointing and self.training:
if use_cache:
logger.warning_once(
"`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
)
use_cache = False
def create_custom_forward(module):
def custom_forward(*inputs):