Improved type hinting for all attention parameters (huggingface#28479)

* Changed type hinting for all attention inputs to 'Optional[Tuple[torch.FloatTensor,...]] = None' * Fixed the ruff formatting issue * fixed type hinting for all hidden_states to 'Optional[Tuple[torch.FloatTensor, ...]] = None' * Changed type hinting in these 12 scripts modeling_dpr.py,modeling_nat.py,idefics/vision.py,modeling_tf_dpr.py,modeling_luke.py,modeling_swin.py,modeling_tf_swin.py,modeling_blip.py,modeling_tf_blip.py,modeling_donut_swin.py,modeling_dinat.py,modeling_swinv2.py * test fail update * fixed type hinting for these 15 scripts modeling_xlnet.py,modeling_tf_xlnet.py,modeling_led.py,modeling_tf_led.py,modleing_rwkv.py,modeling_dpt.py,modeling_tf_cvt.py,modeling_clip.py,modeling_flax_clip.py,modeling_tf_clip.py,modeling_longformer.py,modeling_tf_longformer.py,modeling_siglip.py,modeling_clap.py,modeling_git.py * Changed type hinting in these 12 scripts modeling_dpr.py,modeling_nat.py,idefics/vision.py,modeling_tf_dpr.py,modeling_luke.py,modeling_swin.py,modeling_tf_swin.py,modeling_blip.py,modeling_tf_blip.py,modeling_donut_swin.py,modeling_dinat.py,modeling_swinv2.py * test fail update * Removed the myvenv file * Fixed type hinting for these 8 scripts modeling_tvlt.py,modeling_sam.py,modeling_tf_sam.py,modeling_tvp.py,modeling_rag.py,modeling_tf_rag.py,modeling_tf_xlm.py,modeling_xlm.py
DavidAfonsoValente · Jan 25, 2024 · e4e821c · e4e821c
1 parent a7ede1b
commit e4e821c
Show file tree

Hide file tree

Showing 36 changed files with 408 additions and 408 deletions.
diff --git a/src/transformers/modeling_outputs.py b/src/transformers/modeling_outputs.py
diff --git a/src/transformers/models/blip/modeling_blip.py b/src/transformers/models/blip/modeling_blip.py
@@ -98,8 +98,8 @@ class BlipForConditionalGenerationModelOutput(ModelOutput):
     logits: Optional[Tuple[torch.FloatTensor]] = None
     image_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
     @property
     def decoder_logits(self):
@@ -140,8 +140,8 @@ class BlipTextVisionModelOutput(ModelOutput):
     loss: Optional[torch.FloatTensor] = None
     image_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -181,9 +181,9 @@ class BlipImageTextMatchingModelOutput(ModelOutput):
     loss: Optional[torch.FloatTensor] = None
     image_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
     vision_pooler_output: Optional[torch.FloatTensor] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
     question_embeds: Optional[Tuple[torch.FloatTensor]] = None
 
 

diff --git a/src/transformers/models/blip/modeling_tf_blip.py b/src/transformers/models/blip/modeling_tf_blip.py
@@ -108,8 +108,8 @@ class TFBlipForConditionalGenerationModelOutput(ModelOutput):
     logits: Tuple[tf.Tensor] | None = None
     image_embeds: tf.Tensor | None = None
     last_hidden_state: tf.Tensor = None
-    hidden_states: Tuple[tf.Tensor] | None = None
-    attentions: Tuple[tf.Tensor] | None = None
+    hidden_states: Tuple[tf.Tensor, ...] | None = None
+    attentions: Tuple[tf.Tensor, ...] | None = None
 
     @property
     def decoder_logits(self):
@@ -150,8 +150,8 @@ class TFBlipTextVisionModelOutput(ModelOutput):
     loss: tf.Tensor | None = None
     image_embeds: tf.Tensor | None = None
     last_hidden_state: tf.Tensor = None
-    hidden_states: Tuple[tf.Tensor] | None = None
-    attentions: Tuple[tf.Tensor] | None = None
+    hidden_states: Tuple[tf.Tensor, ...] | None = None
+    attentions: Tuple[tf.Tensor, ...] | None = None
 
 
 @dataclass
@@ -191,9 +191,9 @@ class TFBlipImageTextMatchingModelOutput(ModelOutput):
     loss: tf.Tensor | None = None
     image_embeds: tf.Tensor | None = None
     last_hidden_state: tf.Tensor = None
-    hidden_states: Tuple[tf.Tensor] | None = None
+    hidden_states: Tuple[tf.Tensor, ...] | None = None
     vision_pooler_output: tf.Tensor | None = None
-    attentions: Tuple[tf.Tensor] | None = None
+    attentions: Tuple[tf.Tensor, ...] | None = None
     question_embeds: Tuple[tf.Tensor] | None = None
 
 

diff --git a/src/transformers/models/clap/modeling_clap.py b/src/transformers/models/clap/modeling_clap.py
@@ -159,8 +159,8 @@ class ClapTextModelOutput(ModelOutput):
 
     text_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -188,8 +188,8 @@ class ClapAudioModelOutput(ModelOutput):
 
     audio_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass

diff --git a/src/transformers/models/clip/modeling_clip.py b/src/transformers/models/clip/modeling_clip.py
@@ -83,8 +83,8 @@ class CLIPVisionModelOutput(ModelOutput):
 
     image_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -112,8 +112,8 @@ class CLIPTextModelOutput(ModelOutput):
 
     text_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass

diff --git a/src/transformers/models/clip/modeling_flax_clip.py b/src/transformers/models/clip/modeling_flax_clip.py
@@ -182,8 +182,8 @@ class FlaxCLIPTextModelOutput(ModelOutput):
 
     text_embeds: jnp.ndarray = None
     last_hidden_state: jnp.ndarray = None
-    hidden_states: Optional[Tuple[jnp.ndarray]] = None
-    attentions: Optional[Tuple[jnp.ndarray]] = None
+    hidden_states: Optional[Tuple[jnp.ndarray, ...]] = None
+    attentions: Optional[Tuple[jnp.ndarray, ...]] = None
 
 
 @flax.struct.dataclass

diff --git a/src/transformers/models/cvt/modeling_cvt.py b/src/transformers/models/cvt/modeling_cvt.py
@@ -74,7 +74,7 @@ class BaseModelOutputWithCLSToken(ModelOutput):
 
     last_hidden_state: torch.FloatTensor = None
     cls_token_value: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 # Copied from transformers.models.beit.modeling_beit.drop_path

diff --git a/src/transformers/models/cvt/modeling_tf_cvt.py b/src/transformers/models/cvt/modeling_tf_cvt.py
@@ -77,7 +77,7 @@ class TFBaseModelOutputWithCLSToken(ModelOutput):
 
     last_hidden_state: tf.Tensor = None
     cls_token_value: tf.Tensor = None
-    hidden_states: Tuple[tf.Tensor] | None = None
+    hidden_states: Tuple[tf.Tensor, ...] | None = None
 
 
 class TFCvtDropPath(tf.keras.layers.Layer):

diff --git a/src/transformers/models/dinat/modeling_dinat.py b/src/transformers/models/dinat/modeling_dinat.py
@@ -105,9 +105,9 @@ class DinatEncoderOutput(ModelOutput):
     """
 
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
-    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -142,9 +142,9 @@ class DinatModelOutput(ModelOutput):
 
     last_hidden_state: torch.FloatTensor = None
     pooler_output: Optional[torch.FloatTensor] = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
-    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -179,9 +179,9 @@ class DinatImageClassifierOutput(ModelOutput):
 
     loss: Optional[torch.FloatTensor] = None
     logits: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
-    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 # Copied from transformers.models.nat.modeling_nat.NatEmbeddings with Nat->Dinat

diff --git a/src/transformers/models/donut/modeling_donut_swin.py b/src/transformers/models/donut/modeling_donut_swin.py
@@ -83,9 +83,9 @@ class DonutSwinEncoderOutput(ModelOutput):
     """
 
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
-    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -120,9 +120,9 @@ class DonutSwinModelOutput(ModelOutput):
 
     last_hidden_state: torch.FloatTensor = None
     pooler_output: Optional[torch.FloatTensor] = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
-    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    reshaped_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 # Copied from transformers.models.swin.modeling_swin.window_partition

diff --git a/src/transformers/models/dpr/modeling_dpr.py b/src/transformers/models/dpr/modeling_dpr.py
@@ -82,8 +82,8 @@ class DPRContextEncoderOutput(ModelOutput):
     """
 
     pooler_output: torch.FloatTensor
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -110,8 +110,8 @@ class DPRQuestionEncoderOutput(ModelOutput):
     """
 
     pooler_output: torch.FloatTensor
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -143,8 +143,8 @@ class DPRReaderOutput(ModelOutput):
     start_logits: torch.FloatTensor
     end_logits: torch.FloatTensor = None
     relevance_logits: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 class DPRPreTrainedModel(PreTrainedModel):

diff --git a/src/transformers/models/dpr/modeling_tf_dpr.py b/src/transformers/models/dpr/modeling_tf_dpr.py
@@ -82,8 +82,8 @@ class TFDPRContextEncoderOutput(ModelOutput):
     """
 
     pooler_output: tf.Tensor = None
-    hidden_states: Tuple[tf.Tensor] | None = None
-    attentions: Tuple[tf.Tensor] | None = None
+    hidden_states: Tuple[tf.Tensor, ...] | None = None
+    attentions: Tuple[tf.Tensor, ...] | None = None
 
 
 @dataclass
@@ -110,8 +110,8 @@ class TFDPRQuestionEncoderOutput(ModelOutput):
     """
 
     pooler_output: tf.Tensor = None
-    hidden_states: Tuple[tf.Tensor] | None = None
-    attentions: Tuple[tf.Tensor] | None = None
+    hidden_states: Tuple[tf.Tensor, ...] | None = None
+    attentions: Tuple[tf.Tensor, ...] | None = None
 
 
 @dataclass
@@ -143,8 +143,8 @@ class TFDPRReaderOutput(ModelOutput):
     start_logits: tf.Tensor = None
     end_logits: tf.Tensor = None
     relevance_logits: tf.Tensor = None
-    hidden_states: Tuple[tf.Tensor] | None = None
-    attentions: Tuple[tf.Tensor] | None = None
+    hidden_states: Tuple[tf.Tensor, ...] | None = None
+    attentions: Tuple[tf.Tensor, ...] | None = None
 
 
 class TFDPREncoderLayer(tf.keras.layers.Layer):

diff --git a/src/transformers/models/dpt/modeling_dpt.py b/src/transformers/models/dpt/modeling_dpt.py
@@ -76,7 +76,7 @@ class BaseModelOutputWithIntermediateActivations(ModelOutput):
     """
 
     last_hidden_states: torch.FloatTensor = None
-    intermediate_activations: Optional[Tuple[torch.FloatTensor]] = None
+    intermediate_activations: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -110,9 +110,9 @@ class BaseModelOutputWithPoolingAndIntermediateActivations(ModelOutput):
 
     last_hidden_state: torch.FloatTensor = None
     pooler_output: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
-    intermediate_activations: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    intermediate_activations: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 class DPTViTHybridEmbeddings(nn.Module):

diff --git a/src/transformers/models/git/modeling_git.py b/src/transformers/models/git/modeling_git.py
@@ -77,8 +77,8 @@ class GitVisionModelOutput(ModelOutput):
 
     image_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 class GitEmbeddings(nn.Module):

diff --git a/src/transformers/models/idefics/vision.py b/src/transformers/models/idefics/vision.py
@@ -57,8 +57,8 @@ class IdeficsVisionModelOutput(ModelOutput):
 
     image_embeds: Optional[torch.FloatTensor] = None
     last_hidden_state: torch.FloatTensor = None
-    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
+    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 # Adapted from transformers.models.clip.modeling_clip.CLIPVisionEmbeddings