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

.gitignore

@@ -102,7 +102,6 @@ venv/
 ENV/
 env.bak/
 venv.bak/
-myvenv/
 
 # Spyder project settings
 .spyderproject

src/transformers/models/rag/modeling_rag.py

@@ -120,14 +120,14 @@ class RetrievAugLMMarginOutput(ModelOutput):
     context_input_ids: Optional[torch.LongTensor] = None
     context_attention_mask: Optional[torch.LongTensor] = None
     question_encoder_last_hidden_state: Optional[torch.FloatTensor] = None
-    question_enc_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    question_enc_attentions: Optional[Tuple[torch.FloatTensor]] = None
+    question_enc_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    question_enc_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
     generator_enc_last_hidden_state: Optional[torch.FloatTensor] = None
-    generator_enc_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    generator_enc_attentions: Optional[Tuple[torch.FloatTensor]] = None
-    generator_dec_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    generator_dec_attentions: Optional[Tuple[torch.FloatTensor]] = None
-    generator_cross_attentions: Optional[Tuple[torch.FloatTensor]] = None
+    generator_enc_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    generator_enc_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    generator_dec_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    generator_dec_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    generator_cross_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 @dataclass
@@ -210,14 +210,14 @@ class RetrievAugLMOutput(ModelOutput):
     context_input_ids: Optional[torch.LongTensor] = None
     context_attention_mask: Optional[torch.LongTensor] = None
     question_encoder_last_hidden_state: Optional[torch.FloatTensor] = None
-    question_enc_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    question_enc_attentions: Optional[Tuple[torch.FloatTensor]] = None
+    question_enc_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    question_enc_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
     generator_enc_last_hidden_state: Optional[torch.FloatTensor] = None
-    generator_enc_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    generator_enc_attentions: Optional[Tuple[torch.FloatTensor]] = None
-    generator_dec_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    generator_dec_attentions: Optional[Tuple[torch.FloatTensor]] = None
-    generator_cross_attentions: Optional[Tuple[torch.FloatTensor]] = None
+    generator_enc_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    generator_enc_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    generator_dec_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    generator_dec_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    generator_cross_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 class RagPreTrainedModel(PreTrainedModel):

src/transformers/models/rag/modeling_tf_rag.py

@@ -123,13 +123,13 @@ class TFRetrievAugLMMarginOutput(ModelOutput):
     context_input_ids: tf.Tensor | None = None
     context_attention_mask: tf.Tensor | None = None
     question_encoder_last_hidden_state: tf.Tensor | None = None
-    question_enc_hidden_states: Tuple[tf.Tensor] | None = None
-    question_enc_attentions: Tuple[tf.Tensor] | None = None
+    question_enc_hidden_states: Tuple[tf.Tensor, ...] | None = None
+    question_enc_attentions: Tuple[tf.Tensor, ...] | None = None
     generator_enc_last_hidden_state: tf.Tensor | None = None
-    generator_enc_hidden_states: Tuple[tf.Tensor] | None = None
-    generator_enc_attentions: Tuple[tf.Tensor] | None = None
-    generator_dec_hidden_states: Tuple[tf.Tensor] | None = None
-    generator_dec_attentions: Tuple[tf.Tensor] | None = None
+    generator_enc_hidden_states: Tuple[tf.Tensor, ...] | None = None
+    generator_enc_attentions: Tuple[tf.Tensor, ...] | None = None
+    generator_dec_hidden_states: Tuple[tf.Tensor, ...] | None = None
+    generator_dec_attentions: Tuple[tf.Tensor, ...] | None = None
 
 
 @dataclass
@@ -206,13 +206,13 @@ class TFRetrievAugLMOutput(ModelOutput):
     context_input_ids: tf.Tensor | None = None
     context_attention_mask: tf.Tensor | None = None
     question_encoder_last_hidden_state: tf.Tensor | None = None
-    question_enc_hidden_states: Tuple[tf.Tensor] | None = None
-    question_enc_attentions: Tuple[tf.Tensor] | None = None
+    question_enc_hidden_states: Tuple[tf.Tensor, ...] | None = None
+    question_enc_attentions: Tuple[tf.Tensor, ...] | None = None
     generator_enc_last_hidden_state: tf.Tensor | None = None
-    generator_enc_hidden_states: Tuple[tf.Tensor] | None = None
-    generator_enc_attentions: Tuple[tf.Tensor] | None = None
-    generator_dec_hidden_states: Tuple[tf.Tensor] | None = None
-    generator_dec_attentions: Tuple[tf.Tensor] | None = None
+    generator_enc_hidden_states: Tuple[tf.Tensor, ...] | None = None
+    generator_enc_attentions: Tuple[tf.Tensor, ...] | None = None
+    generator_dec_hidden_states: Tuple[tf.Tensor, ...] | None = None
+    generator_dec_attentions: Tuple[tf.Tensor, ...] | None = None
 
 
 class TFRagPreTrainedModel(TFPreTrainedModel):

src/transformers/models/sam/modeling_sam.py

@@ -71,8 +71,8 @@ class SamVisionEncoderOutput(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
@@ -106,9 +106,9 @@ class SamImageSegmentationOutput(ModelOutput):
 
     iou_scores: torch.FloatTensor = None
     pred_masks: torch.FloatTensor = None
-    vision_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
-    vision_attentions: Optional[Tuple[torch.FloatTensor]] = None
-    mask_decoder_attentions: Optional[Tuple[torch.FloatTensor]] = None
+    vision_hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
+    vision_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
+    mask_decoder_attentions: Optional[Tuple[torch.FloatTensor, ...]] = None
 
 
 class SamPatchEmbeddings(nn.Module):

src/transformers/models/sam/modeling_tf_sam.py

@@ -74,8 +74,8 @@ class TFSamVisionEncoderOutput(ModelOutput):
 
     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
@@ -109,9 +109,9 @@ class TFSamImageSegmentationOutput(ModelOutput):
 
     iou_scores: tf.Tensor = None
     pred_masks: tf.Tensor = None
-    vision_hidden_states: Tuple[tf.Tensor] | None = None
-    vision_attentions: Tuple[tf.Tensor] | None = None
-    mask_decoder_attentions: Tuple[tf.Tensor] | None = None
+    vision_hidden_states: Tuple[tf.Tensor, ...] | None = None
+    vision_attentions: Tuple[tf.Tensor, ...] | None = None
+    mask_decoder_attentions: Tuple[tf.Tensor, ...] | None = None
 
 
 class TFSamPatchEmbeddings(tf.keras.layers.Layer):

src/transformers/models/tvlt/modeling_tvlt.py

@@ -88,8 +88,8 @@ class TvltModelOutput(ModelOutput):
     audio_label_masks: torch.LongTensor = None
     pixel_ids_restore: torch.LongTensor = None
     audio_ids_restore: torch.LongTensor = 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
@@ -111,8 +111,8 @@ class TvltDecoderOutput(ModelOutput):
     """
 
     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
 
 
 @dataclass
@@ -145,8 +145,8 @@ class TvltForPreTrainingOutput(ModelOutput):
     matching_logits: torch.FloatTensor = None
     pixel_logits: torch.FloatTensor = None
     audio_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
 
 
 def generate_pixel_mask_noise(pixel_values, pixel_mask=None, mask_ratio=0.75):

src/transformers/models/tvp/modeling_tvp.py

@@ -61,8 +61,8 @@ class TvpVideoGroundingOutput(ModelOutput):
 
     loss: Optional[torch.FloatTensor] = None
     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 TvpLoss(nn.Module):

src/transformers/models/xlm/modeling_tf_xlm.py

@@ -614,8 +614,8 @@ class TFXLMWithLMHeadModelOutput(ModelOutput):
     """
 
     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
 
 
 XLM_START_DOCSTRING = r"""

src/transformers/models/xlm/modeling_xlm.py

@@ -297,8 +297,8 @@ class XLMForQuestionAnsweringOutput(ModelOutput):
     end_top_log_probs: Optional[torch.FloatTensor] = None
     end_top_index: Optional[torch.LongTensor] = None
     cls_logits: Optional[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
 
 
 XLM_START_DOCSTRING = r"""