riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-16 11:08:23 +06:00
Code Issues Actions 28 Packages Projects Releases Wiki Activity

Add many missing spaces in adjacent strings (#26751)

Browse Source 
Add missing spaces in adjacent strings
This commit is contained in:
Tom Aarsen 2023-10-12 10:28:40 +02:00 committed by GitHub
parent 3bc65505fc
commit 40ea9ab2a1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
154 changed files with 331 additions and 331 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/pytorch/translation/run_translation_no_trainer.py
View File

@ -118,7 +118,7 @@ def parse_args():
default=128,
help=(
"The maximum total sequence length for target text after "
"tokenization. Sequences longer than this will be truncated, sequences shorter will be padded."
"tokenization. Sequences longer than this will be truncated, sequences shorter will be padded "
"during ``evaluate`` and ``predict``."
),
)

2
examples/research_projects/robust-speech-event/run_speech_recognition_ctc_bnb.py
View File

@ -399,7 +399,7 @@ def main():
# Log on each process the small summary:
logger.warning(
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}, "
f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
)
# Set the verbosity to info of the Transformers logger (on main process only):

2
examples/research_projects/robust-speech-event/run_speech_recognition_ctc_streaming.py
View File

@ -354,7 +354,7 @@ def main():
# Log on each process the small summary:
logger.warning(
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}, "
f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
)
# Set the verbosity to info of the Transformers logger (on main process only):

2
examples/research_projects/xtreme-s/run_xtreme_s.py
View File

@ -455,7 +455,7 @@ def main():
# Log on each process the small summary:
logger.warning(
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}, "
f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
)
# Set the verbosity to info of the Transformers logger (on main process only):

2
src/transformers/models/idefics/vision.py
View File

@ -116,7 +116,7 @@ class IdeficsVisionEmbeddings(nn.Module):
if fp32_upcasting:
logger.warning_once(
"Upcasting patch_pos_embed to fp32 for interpolation since `upsample_bicubic2d_out_frame` in nn.functional.interpolate "
"is not implemented for 'torch.bfloat16' dtype. This will result in a slight overhead"
"is not implemented for 'torch.bfloat16' dtype. This will result in a slight overhead."
)
patch_pos_embed = patch_pos_embed.to(torch.float)
patch_pos_embed = nn.functional.interpolate(

6
src/transformers/models/switch_transformers/modeling_switch_transformers.py
View File

@ -1774,13 +1774,13 @@ class SwitchTransformersForConditionalGeneration(SwitchTransformersPreTrainedMod
if reordered_layer_past_states[0].shape != layer_past_states[0].shape:
raise ValueError(
"expected reordered_layer_past_states to have the same shape than layer_past_states"
"expected reordered_layer_past_states to have the same shape than layer_past_states, "
f"but got {reordered_layer_past_states[0].shape} and {layer_past_states[0].shape}"
)
if len(reordered_layer_past_states) != len(layer_past_states):
raise ValueError(
"expected layer_past_states to have the same length as reordered_layer_past_states"
f"got {len(layer_past_states)} and {len(reordered_layer_past_states)}"
"expected layer_past_states to have the same length as reordered_layer_past_states, "
f"but got {len(layer_past_states)} and {len(reordered_layer_past_states)}"
)
reordered_decoder_past = reordered_decoder_past + (reordered_layer_past_states,)