riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-01 02:31:11 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

CI: more models wo cache support (#30780)

Browse Source
This commit is contained in:
Joao Gante 2024-05-14 10:43:03 +01:00 committed by GitHub
parent 5ad960f1f4
commit d8f8a9cd61
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
7 changed files with 0 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/transformers/models/mistral/modeling_mistral.py
View File

@ -810,7 +810,6 @@ class MistralPreTrainedModel(PreTrainedModel):
_skip_keys_device_placement = "past_key_values" _skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True _supports_flash_attn_2 = True
_supports_sdpa = True _supports_sdpa = True
_supports_cache_class = True
def _init_weights(self, module): def _init_weights(self, module):
std = self.config.initializer_range std = self.config.initializer_range

1
src/transformers/models/mixtral/modeling_mixtral.py
View File

@ -989,7 +989,6 @@ class MixtralPreTrainedModel(PreTrainedModel):
_skip_keys_device_placement = "past_key_values" _skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True _supports_flash_attn_2 = True
_supports_sdpa = True _supports_sdpa = True
_supports_cache_class = True
def _init_weights(self, module): def _init_weights(self, module):
std = self.config.initializer_range std = self.config.initializer_range

1
src/transformers/models/persimmon/modeling_persimmon.py
View File

@ -457,7 +457,6 @@ class PersimmonPreTrainedModel(PreTrainedModel):
supports_gradient_checkpointing = True supports_gradient_checkpointing = True
_no_split_modules = ["PersimmonDecoderLayer"] _no_split_modules = ["PersimmonDecoderLayer"]
_skip_keys_device_placement = "past_key_values" _skip_keys_device_placement = "past_key_values"
_supports_cache_class = True
def _init_weights(self, module): def _init_weights(self, module):
std = self.config.initializer_range std = self.config.initializer_range

1
src/transformers/models/phi/modeling_phi.py
View File

@ -825,7 +825,6 @@ class PhiPreTrainedModel(PreTrainedModel):
_skip_keys_device_placement = "past_key_values" _skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True _supports_flash_attn_2 = True
_supports_sdpa = True _supports_sdpa = True
_supports_cache_class = True
def _init_weights(self, module): def _init_weights(self, module):
std = self.config.initializer_range std = self.config.initializer_range

1
src/transformers/models/phi3/modeling_phi3.py
View File

@ -921,7 +921,6 @@ class Phi3PreTrainedModel(PreTrainedModel):
_skip_keys_device_placement = "past_key_values" _skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True _supports_flash_attn_2 = True
_supports_sdpa = False _supports_sdpa = False
_supports_cache_class = True
_version = "0.0.5" _version = "0.0.5"

1
src/transformers/models/qwen2_moe/modeling_qwen2_moe.py
View File

@ -975,7 +975,6 @@ class Qwen2MoePreTrainedModel(PreTrainedModel):
_skip_keys_device_placement = "past_key_values" _skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True _supports_flash_attn_2 = True
_supports_sdpa = True _supports_sdpa = True
_supports_cache_class = True
def _init_weights(self, module): def _init_weights(self, module):
std = self.config.initializer_range std = self.config.initializer_range

1
src/transformers/models/starcoder2/modeling_starcoder2.py
View File

@ -799,7 +799,6 @@ class Starcoder2PreTrainedModel(PreTrainedModel):
_skip_keys_device_placement = "past_key_values" _skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True _supports_flash_attn_2 = True
_supports_sdpa = True _supports_sdpa = True
_supports_cache_class = True
def _init_weights(self, module): def _init_weights(self, module):
std = self.config.initializer_range std = self.config.initializer_range