Fix Qwen3-VL typos and clarify image/video/vision token descriptions

src/transformers/models/qwen3_vl/configuration_qwen3_vl.py

@@ -110,7 +110,7 @@ class Qwen3VLTextConfig(PreTrainedConfig):
             Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain
             a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE
             with longer `max_position_embeddings`.
-        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+        attention_bias (`bool`, *optional*, defaults to `False`):
             Whether to use a bias in the query, key, value and output projection layers during self-attention.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
@@ -197,13 +197,13 @@ class Qwen3VLConfig(PreTrainedConfig):
         vision_config (`Union[PreTrainedConfig, dict]`,  *optional*, defaults to `Qwen3VLVisionConfig`):
             The config object or dictionary of the vision backbone.
         image_token_id (`int`, *optional*, defaults to 151655):
-            The image token index to encode the image prompt.
+            The token id used as the placeholder for image inputs.
         video_token_id (`int`, *optional*, defaults to 151656):
-            The video token index to encode the image prompt.
+            The token id used as the placeholder for video inputs.
         vision_start_token_id (`int`, *optional*, defaults to 151652):
-            The start token index to encode the image prompt.
+            The token id that marks the start of a vision segment (image or video).
         vision_end_token_id (`int`, *optional*, defaults to 151653):
-            The end token index to encode the image prompt.
+            The token id that marks the end of a vision segment (image or video).
         tie_word_embeddings (`bool`, *optional*, defaults to `False`):
             Whether to tie the word embeddings.
 

src/transformers/models/qwen3_vl/modular_qwen3_vl.py

@@ -152,7 +152,7 @@ class Qwen3VLTextConfig(PreTrainedConfig):
             Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain
             a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE
             with longer `max_position_embeddings`.
-        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+        attention_bias (`bool`, *optional*, defaults to `False`):
             Whether to use a bias in the query, key, value and output projection layers during self-attention.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
@@ -239,13 +239,13 @@ class Qwen3VLConfig(PreTrainedConfig):
         vision_config (`Union[PreTrainedConfig, dict]`,  *optional*, defaults to `Qwen3VLVisionConfig`):
             The config object or dictionary of the vision backbone.
         image_token_id (`int`, *optional*, defaults to 151655):
-            The image token index to encode the image prompt.
+            The token id used as the placeholder for image inputs.
         video_token_id (`int`, *optional*, defaults to 151656):
-            The video token index to encode the image prompt.
+            The token id used as the placeholder for video inputs.
         vision_start_token_id (`int`, *optional*, defaults to 151652):
-            The start token index to encode the image prompt.
+            The token id that marks the start of a vision segment (image or video).
         vision_end_token_id (`int`, *optional*, defaults to 151653):
-            The end token index to encode the image prompt.
+            The token id that marks the end of a vision segment (image or video).
         tie_word_embeddings (`bool`, *optional*, defaults to `False`):
             Whether to tie the word embeddings.
 
@@ -1404,9 +1404,9 @@ def __call__(
         **kwargs: Unpack[Qwen3VLProcessorKwargs],
     ) -> BatchFeature:
         """
-        Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
+        Main method to prepare for the model one or several sequence(s) and image(s). This method forwards the `text`
         and `kwargs` arguments to Qwen2TokenizerFast's [`~Qwen2TokenizerFast.__call__`] if `text` is not `None` to encode
-        the text. To prepare the vision inputs, this method forwards the `vision_infos` and `kwrags` arguments to
+        the text. To prepare the vision inputs, this method forwards the `vision_infos` and `kwargs` arguments to
         Qwen2VLImageProcessor's [`~Qwen2VLImageProcessor.__call__`] if `vision_infos` is not `None`.
 
         Args:
@@ -1418,7 +1418,7 @@ def __call__(
                 (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                 `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
             videos (`np.ndarray`, `torch.Tensor`, `list[np.ndarray]`, `list[torch.Tensor]`):
-                The image or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch
+                The video or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch
                 tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported.
             return_tensors (`str` or [`~utils.TensorType`], *optional*):
                 If set, will return tensors of a particular framework. Acceptable values are:

src/transformers/models/qwen3_vl/processing_qwen3_vl.py

@@ -99,9 +99,9 @@ def __call__(
         **kwargs: Unpack[Qwen3VLProcessorKwargs],
     ) -> BatchFeature:
         """
-        Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
+        Main method to prepare for the model one or several sequence(s) and image(s). This method forwards the `text`
         and `kwargs` arguments to Qwen2TokenizerFast's [`~Qwen2TokenizerFast.__call__`] if `text` is not `None` to encode
-        the text. To prepare the vision inputs, this method forwards the `vision_infos` and `kwrags` arguments to
+        the text. To prepare the vision inputs, this method forwards the `vision_infos` and `kwargs` arguments to
         Qwen2VLImageProcessor's [`~Qwen2VLImageProcessor.__call__`] if `vision_infos` is not `None`.
 
         Args:
@@ -113,7 +113,7 @@ def __call__(
                 (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                 `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
             videos (`np.ndarray`, `torch.Tensor`, `list[np.ndarray]`, `list[torch.Tensor]`):
-                The image or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch
+                The video or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch
                 tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported.
             return_tensors (`str` or [`~utils.TensorType`], *optional*):
                 If set, will return tensors of a particular framework. Acceptable values are: