riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-03 03:31:05 +06:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fix DeepSpeed compatibility with weight_norm (#30881) (#31018)

Browse Source
This commit is contained in:
Jonny Li 2024-05-28 12:25:15 -04:00 committed by GitHub
parent aada568f73
commit 476890e9ae
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
10 changed files with 80 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/transformers/models/hubert/modeling_hubert.py
View File

@ -295,8 +295,14 @@ class HubertPositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/seamless_m4t/modeling_seamless_m4t.py
View File

@ -325,8 +325,14 @@ class SeamlessM4TConformerPositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/sew/modeling_sew.py
View File

@ -294,8 +294,14 @@ class SEWPositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = nn.utils.weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = nn.utils.weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/sew_d/modeling_sew_d.py
View File

@ -354,8 +354,14 @@ class SEWDPositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = nn.utils.weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = nn.utils.weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/speecht5/modeling_speecht5.py
View File

@ -368,8 +368,14 @@ class SpeechT5PositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/unispeech/modeling_unispeech.py
View File

@ -330,8 +330,14 @@ class UniSpeechPositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/unispeech_sat/modeling_unispeech_sat.py
View File

@ -347,8 +347,14 @@ class UniSpeechSatPositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/wav2vec2/modeling_wav2vec2.py
View File

@ -398,8 +398,14 @@ class Wav2Vec2PositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py
View File

@ -361,8 +361,14 @@ class Wav2Vec2ConformerPositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = weight_norm(self.conv, name="weight", dim=2)

10
src/transformers/models/wavlm/modeling_wavlm.py
View File

@ -287,8 +287,14 @@ class WavLMPositionalConvEmbedding(nn.Module):
with deepspeed.zero.GatheredParameters(self.conv.weight, modifier_rank=0):
self.conv = weight_norm(self.conv, name="weight", dim=2)
deepspeed.zero.register_external_parameter(self, self.conv.weight_v)
deepspeed.zero.register_external_parameter(self, self.conv.weight_g)
if hasattr(self.conv, "parametrizations"):
weight_g = self.conv.parametrizations.weight.original0
weight_v = self.conv.parametrizations.weight.original1
else:
weight_g = self.conv.weight_g
weight_v = self.conv.weight_v
deepspeed.zero.register_external_parameter(self, weight_v)
deepspeed.zero.register_external_parameter(self, weight_g)
else:
self.conv = weight_norm(self.conv, name="weight", dim=2)