CI: more models wo cache support (#30780)

huggingface · May 14, 2024 · d8f8a9c · d8f8a9c
1 parent 5ad960f
commit d8f8a9c
Show file tree

Hide file tree

Showing 7 changed files with 0 additions and 7 deletions.
diff --git a/src/transformers/models/mistral/modeling_mistral.py b/src/transformers/models/mistral/modeling_mistral.py
@@ -810,7 +810,6 @@ class MistralPreTrainedModel(PreTrainedModel):
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
     _supports_sdpa = True
-    _supports_cache_class = True
 
     def _init_weights(self, module):
         std = self.config.initializer_range

diff --git a/src/transformers/models/mixtral/modeling_mixtral.py b/src/transformers/models/mixtral/modeling_mixtral.py
@@ -989,7 +989,6 @@ class MixtralPreTrainedModel(PreTrainedModel):
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
     _supports_sdpa = True
-    _supports_cache_class = True
 
     def _init_weights(self, module):
         std = self.config.initializer_range

diff --git a/src/transformers/models/persimmon/modeling_persimmon.py b/src/transformers/models/persimmon/modeling_persimmon.py
@@ -457,7 +457,6 @@ class PersimmonPreTrainedModel(PreTrainedModel):
     supports_gradient_checkpointing = True
     _no_split_modules = ["PersimmonDecoderLayer"]
     _skip_keys_device_placement = "past_key_values"
-    _supports_cache_class = True
 
     def _init_weights(self, module):
         std = self.config.initializer_range

diff --git a/src/transformers/models/phi/modeling_phi.py b/src/transformers/models/phi/modeling_phi.py
@@ -825,7 +825,6 @@ class PhiPreTrainedModel(PreTrainedModel):
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
     _supports_sdpa = True
-    _supports_cache_class = True
 
     def _init_weights(self, module):
         std = self.config.initializer_range

diff --git a/src/transformers/models/phi3/modeling_phi3.py b/src/transformers/models/phi3/modeling_phi3.py
@@ -921,7 +921,6 @@ class Phi3PreTrainedModel(PreTrainedModel):
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
     _supports_sdpa = False
-    _supports_cache_class = True
 
     _version = "0.0.5"
 

diff --git a/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py b/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py
@@ -975,7 +975,6 @@ class Qwen2MoePreTrainedModel(PreTrainedModel):
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
     _supports_sdpa = True
-    _supports_cache_class = True
 
     def _init_weights(self, module):
         std = self.config.initializer_range

diff --git a/src/transformers/models/starcoder2/modeling_starcoder2.py b/src/transformers/models/starcoder2/modeling_starcoder2.py
@@ -799,7 +799,6 @@ class Starcoder2PreTrainedModel(PreTrainedModel):
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
     _supports_sdpa = True
-    _supports_cache_class = True
 
     def _init_weights(self, module):
         std = self.config.initializer_range