# Qwen3-VL [Qwen3-VL](https://huggingface.co/papers/2502.13923) is a multimodal vision-language model series, encompassing both dense and MoE variants, as well as Instruct and Thinking versions. Building upon its predecessors, Qwen3-VL delivers significant improvements in visual understanding while maintaining strong pure text capabilities. Key architectural advancements include: enhanced MRope with interleaved layout for better spatial-temporal modeling, DeepStack integration to effectively leverage multi-level features from the Vision Transformer (ViT), and improved video understanding through text-based time alignment—evolving from T-RoPE to text timestamp alignment for more precise temporal grounding. These innovations collectively enable Qwen3-VL to achieve superior performance in complex multimodal tasks. Model usage ```py import torch from transformers import Qwen3VLForConditionalGeneration, AutoProcessor model = Qwen3VLForConditionalGeneration.from_pretrained( "Qwen/Qwen3-VL", dtype=torch.float16, device_map="auto", attn_implementation="sdpa" ) processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL") messages = [ { "role":"user", "content":[ { "type":"image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg" }, { "type":"text", "text":"Describe this image." } ] } ] inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt", ) inputs.pop("token_type_ids", None) generated_ids = model.generate(**inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text) ``` ## Qwen3VLConfig[[transformers.Qwen3VLConfig]] #### transformers.Qwen3VLConfig[[transformers.Qwen3VLConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/configuration_qwen3_vl.py#L107) This is the configuration class to store the configuration of a Qwen3VLModel. It is used to instantiate a Qwen3 Vl model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the [Qwen/Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.5.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.5.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import Qwen3VLForConditionalGeneration, Qwen3VLConfig >>> # Initializing a Qwen3-VL style configuration >>> configuration = Qwen3VLConfig() >>> # Initializing a model from the Qwen3-VL-4B style configuration >>> model = Qwen3VLForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** text_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the text backbone. vision_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the vision backbone. image_token_id (`int`, *optional*, defaults to `151655`) : The image token index used as a placeholder for input images. video_token_id (`int`, *optional*, defaults to `151656`) : The video token index used as a placeholder for input videos. vision_start_token_id (`int`, *optional*, defaults to `151652`) : Token ID that marks the start of a visual segment in the multimodal input sequence. vision_end_token_id (`int`, *optional*, defaults to `151653`) : Token ID that marks the end of a visual segment in the multimodal input sequence. tie_word_embeddings (`bool`, *optional*, defaults to `False`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. ## Qwen3VLTextConfig[[transformers.Qwen3VLTextConfig]] #### transformers.Qwen3VLTextConfig[[transformers.Qwen3VLTextConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/configuration_qwen3_vl.py#L59) This is the configuration class to store the configuration of a Qwen3VLModel. It is used to instantiate a Qwen3 Vl model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the [Qwen/Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.5.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.5.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import Qwen3VLTextModel, Qwen3VLTextConfig >>> # Initializing a Qwen3VL style configuration >>> configuration = Qwen3VLTextConfig() >>> # Initializing a model from the Qwen3-VL-7B style configuration >>> model = Qwen3VLTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** vocab_size (`int`, *optional*, defaults to `151936`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`. hidden_size (`int`, *optional*, defaults to `4096`) : Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to `22016`) : Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to `32`) : Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to `32`) : Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to `32`) : This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`. head_dim (`int`, *optional*, defaults to `128`) : The attention head dimension. If None, it will default to hidden_size // num_attention_heads hidden_act (`str`, *optional*, defaults to `silu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. max_position_embeddings (`int`, *optional*, defaults to `128000`) : The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`float`, *optional*, defaults to `1e-06`) : The epsilon used by the rms normalization layers. use_cache (`bool`, *optional*, defaults to `True`) : Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True` or when the model is a decoder-only generative model. rope_parameters (`Union[~modeling_rope_utils.RopeParameters, dict]`, *optional*) : 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`, *optional*, defaults to `False`) : Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. pad_token_id (`int`, *optional*) : Token id used for padding in the vocabulary. ## Qwen3VLProcessor[[transformers.Qwen3VLProcessor]] #### transformers.Qwen3VLProcessor[[transformers.Qwen3VLProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/processing_qwen3_vl.py#L46) Constructs a Qwen3VLProcessor which wraps a image processor, a tokenizer, and a video processor into a single processor. [Qwen3VLProcessor](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLProcessor) offers all the functionalities of [Qwen2VLImageProcessor](/docs/transformers/v5.5.0/en/model_doc/qwen2_vl#transformers.Qwen2VLImageProcessor), [Qwen2Tokenizer](/docs/transformers/v5.5.0/en/model_doc/qwen2#transformers.Qwen2Tokenizer), and [Qwen3VLVideoProcessor](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLVideoProcessor). See the [~Qwen2VLImageProcessor](/docs/transformers/v5.5.0/en/model_doc/qwen2_vl#transformers.Qwen2VLImageProcessor), [~Qwen2Tokenizer](/docs/transformers/v5.5.0/en/model_doc/qwen2#transformers.Qwen2Tokenizer), and [~Qwen3VLVideoProcessor](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLVideoProcessor) for more information. __call__transformers.Qwen3VLProcessor.__call__https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/processing_qwen3_vl.py#L78[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']] = None"}, {"name": "text", "val": ": str | list[str] | list[list[str]] = None"}, {"name": "videos", "val": ": typing.Union[list['PIL.Image.Image'], numpy.ndarray, ForwardRef('torch.Tensor'), list[numpy.ndarray], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list[numpy.ndarray]], list[list['torch.Tensor']], transformers.video_utils.URL, list[transformers.video_utils.URL], list[list[transformers.video_utils.URL]], transformers.video_utils.Path, list[transformers.video_utils.Path], list[list[transformers.video_utils.Path]]] = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.qwen3_vl.processing_qwen3_vl.Qwen3VLProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`, *optional*) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **text** (`Union[str, list[str], list[list[str]]]`, *optional*) -- The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If you pass a pretokenized input, set `is_split_into_words=True` to avoid ambiguity with batched inputs. - **videos** (`Union[list[PIL.Image.Image], numpy.ndarray, torch.Tensor, list[numpy.ndarray], list[torch.Tensor], list[list[PIL.Image.Image]], list[list[numpy.ndarray]], list[list[torch.Tensor]], ~video_utils.URL, list[~video_utils.URL], list[list[~video_utils.URL]], ~video_utils.Path, list[~video_utils.Path], list[list[~video_utils.Path]]]`, *optional*) -- Video to preprocess. Expects a single or batch of videos with pixel values ranging from 0 to 255. If passing in videos with pixel values between 0 and 1, set `do_rescale=False`. - **return_tensors** (`str` or [TensorType](/docs/transformers/v5.5.0/en/internal/file_utils#transformers.TensorType), *optional*) -- If set, will return tensors of a particular framework. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - ****kwargs** ([ProcessingKwargs](/docs/transformers/v5.5.0/en/main_classes/processors#transformers.ProcessingKwargs), *optional*) -- Additional processing options for each modality (text, images, videos, audio). Model-specific parameters are listed above; see the TypedDict class for the complete list of supported arguments.0[BatchFeature](/docs/transformers/v5.5.0/en/main_classes/feature_extractor#transformers.BatchFeature)A [BatchFeature](/docs/transformers/v5.5.0/en/main_classes/feature_extractor#transformers.BatchFeature) with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. - **pixel_values_videos** -- Pixel values of videos to be fed to a model. Returned when `videos` is not `None`. - **image_grid_thw** -- List of image 3D grid in LLM. Returned when `images` is not `None`. - **video_grid_thw** -- List of video 3D grid in LLM. Returned when `videos` is not `None`. **Parameters:** image_processor (`Qwen2VLImageProcessor`) : The image processor is a required input. tokenizer (`Qwen2Tokenizer`) : The tokenizer is a required input. video_processor (`Qwen3VLVideoProcessor`) : The video processor is a required input. chat_template (`str`) : A Jinja template to convert lists of messages in a chat into a tokenizable string. **Returns:** `[BatchFeature](/docs/transformers/v5.5.0/en/main_classes/feature_extractor#transformers.BatchFeature)` A [BatchFeature](/docs/transformers/v5.5.0/en/main_classes/feature_extractor#transformers.BatchFeature) with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. - **pixel_values_videos** -- Pixel values of videos to be fed to a model. Returned when `videos` is not `None`. - **image_grid_thw** -- List of image 3D grid in LLM. Returned when `images` is not `None`. - **video_grid_thw** -- List of video 3D grid in LLM. Returned when `videos` is not `None`. ## Qwen3VLVideoProcessor[[transformers.Qwen3VLVideoProcessor]] #### transformers.Qwen3VLVideoProcessor[[transformers.Qwen3VLVideoProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/video_processing_qwen3_vl.py#L86) Constructs a fast Qwen3-VL image processor that dynamically resizes videos based on the original videos. sample_framestransformers.Qwen3VLVideoProcessor.sample_frameshttps://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/video_processing_qwen3_vl.py#L119[{"name": "metadata", "val": ": VideoMetadata"}, {"name": "num_frames", "val": ": int | None = None"}, {"name": "fps", "val": ": int | float | None = None"}, {"name": "**kwargs", "val": ""}]- **video** (`torch.Tensor`) -- Video that need to be sampled. - **metadata** (`VideoMetadata`) -- Metadata of the video containing information about total duration, fps and total number of frames. - **num_frames** (`int`, *optional*) -- Maximum number of frames to sample. Defaults to `self.num_frames`. - **fps** (`int` or `float`, *optional*) -- Target frames to sample per second. Defaults to `self.fps`.0torch.TensorSampled video frames. Default sampling function which uniformly samples the desired number of frames between 0 and total number of frames. If `fps` is passed along with metadata, `fps` frames per second are sampled uniformty. Arguments `num_frames` and `fps` are mutually exclusive. **Parameters:** do_resize (`bool`, *optional*, defaults to `self.do_resize`) : Whether to resize the video's (height, width) dimensions to the specified `size`. Can be overridden by the `do_resize` parameter in the `preprocess` method. size (`dict`, *optional*, defaults to `self.size`) : Size of the output video after resizing. Can be overridden by the `size` parameter in the `preprocess` method. size_divisor (`int`, *optional*, defaults to `self.size_divisor`) : The size by which to make sure both the height and width can be divided. default_to_square (`bool`, *optional*, defaults to `self.default_to_square`) : Whether to default to a square video when resizing, if size is an int. resample (`PILImageResampling`, *optional*, defaults to `self.resample`) : Resampling filter to use if resizing the video. Only has an effect if `do_resize` is set to `True`. Can be overridden by the `resample` parameter in the `preprocess` method. do_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`) : Whether to center crop the video to the specified `crop_size`. Can be overridden by `do_center_crop` in the `preprocess` method. crop_size (`dict[str, int]` *optional*, defaults to `self.crop_size`) : Size of the output video after applying `center_crop`. Can be overridden by `crop_size` in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`) : Whether to rescale the video by the specified scale `rescale_factor`. Can be overridden by the `do_rescale` parameter in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `self.rescale_factor`) : Scale factor to use if rescaling the video. Only has an effect if `do_rescale` is set to `True`. Can be overridden by the `rescale_factor` parameter in the `preprocess` method. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`) : Whether to normalize the video. Can be overridden by the `do_normalize` parameter in the `preprocess` method. Can be overridden by the `do_normalize` parameter in the `preprocess` method. image_mean (`float` or `list[float]`, *optional*, defaults to `self.image_mean`) : Mean to use if normalizing the video. This is a float or list of floats the length of the number of channels in the video. Can be overridden by the `image_mean` parameter in the `preprocess` method. Can be overridden by the `image_mean` parameter in the `preprocess` method. image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`) : Standard deviation to use if normalizing the video. This is a float or list of floats the length of the number of channels in the video. Can be overridden by the `image_std` parameter in the `preprocess` method. Can be overridden by the `image_std` parameter in the `preprocess` method. do_convert_rgb (`bool`, *optional*, defaults to `self.image_std`) : Whether to convert the video to RGB. video_metadata (`VideoMetadata`, *optional*) : Metadata of the video containing information about total duration, fps and total number of frames. do_sample_frames (`int`, *optional*, defaults to `self.do_sample_frames`) : Whether to sample frames from the video before processing or to process the whole video. num_frames (`int`, *optional*, defaults to `self.num_frames`) : Maximum number of frames to sample when `do_sample_frames=True`. fps (`int` or `float`, *optional*, defaults to `self.fps`) : Target frames to sample per second when `do_sample_frames=True`. return_tensors (`str` or `TensorType`, *optional*) : Returns stacked tensors if set to `pt, otherwise returns a list of tensors. data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`) : The channel dimension format for the output video. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: video in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: video in (height, width, num_channels) format. - Unset: Use the channel dimension format of the input video. input_data_format (`ChannelDimension` or `str`, *optional*) : The channel dimension format for the input video. If unset, the channel dimension format is inferred from the input video. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: video in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: video in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: video in (height, width) format. device (`torch.device`, *optional*) : The device to process the videos on. If unset, the device is inferred from the input videos. return_metadata (`bool`, *optional*) : Whether to return video metadata or not. patch_size (`int`, *optional*, defaults to 16) : The spacial patch size of the vision encoder. temporal_patch_size (`int`, *optional*, defaults to 2) : The temporal patch size of the vision encoder. merge_size (`int`, *optional*, defaults to 2) : The merge size of the vision encoder to llm encoder. **Returns:** `torch.Tensor` Sampled video frames. ## Qwen3VLVisionModel[[transformers.Qwen3VLVisionModel]] #### transformers.Qwen3VLVisionModel[[transformers.Qwen3VLVisionModel]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L616) forwardtransformers.Qwen3VLVisionModel.forwardhttps://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L765[{"name": "hidden_states", "val": ": Tensor"}, {"name": "grid_thw", "val": ": Tensor"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **hidden_states** (`torch.Tensor` of shape `(seq_len, hidden_size)`) -- The final hidden states of the model. - **grid_thw** (`torch.Tensor` of shape `(num_images_or_videos, 3)`) -- The temporal, height and width of feature shape of each image in LLM.0`torch.Tensor`hidden_states. **Parameters:** hidden_states (`torch.Tensor` of shape `(seq_len, hidden_size)`) : The final hidden states of the model. grid_thw (`torch.Tensor` of shape `(num_images_or_videos, 3)`) : The temporal, height and width of feature shape of each image in LLM. **Returns:** ``torch.Tensor`` hidden_states. ## Qwen3VLTextModel[[transformers.Qwen3VLTextModel]] #### transformers.Qwen3VLTextModel[[transformers.Qwen3VLTextModel]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L832) Text part of Qwen3VL, not a pure text-only model, as DeepStack integrates visual features into the early hidden states. This model inherits from [PreTrainedModel](/docs/transformers/v5.5.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.Qwen3VLTextModel.forwardhttps://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L853[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "visual_pos_masks", "val": ": torch.Tensor | None = None"}, {"name": "deepstack_visual_embeds", "val": ": list[torch.Tensor] | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.modeling_flash_attention_utils.FlashAttentionKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.5.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/v5.5.0/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.5.0/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **use_cache** (`bool`, *optional*) -- If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). - **visual_pos_masks** (`torch.Tensor` of shape `(batch_size, seqlen)`, *optional*) -- The mask of the visual positions. - **deepstack_visual_embeds** (`list[torch.Tensor]`, *optional*) -- The deepstack visual embeddings. The shape is (num_layers, visual_seqlen, embed_dim). The feature is extracted from the different visual encoder layers, and fed to the decoder hidden states. It's from the paper DeepStack(https://arxiv.org/abs/2406.04334).0[BaseModelOutputWithPast](/docs/transformers/v5.5.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPast](/docs/transformers/v5.5.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Qwen3VLConfig](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLConfig)) and inputs. The [Qwen3VLTextModel](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLTextModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output. - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.5.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. **Parameters:** config ([Qwen3VLTextConfig](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLTextConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.5.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[BaseModelOutputWithPast](/docs/transformers/v5.5.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPast](/docs/transformers/v5.5.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Qwen3VLConfig](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLConfig)) and inputs. ## Qwen3VLModel[[transformers.Qwen3VLModel]] #### transformers.Qwen3VLModel[[transformers.Qwen3VLModel]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L953) The bare Qwen3 Vl Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.5.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.Qwen3VLModel.forwardhttps://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L1256[{"name": "input_ids", "val": ": LongTensor = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "pixel_values", "val": ": torch.Tensor | None = None"}, {"name": "pixel_values_videos", "val": ": torch.FloatTensor | None = None"}, {"name": "image_grid_thw", "val": ": torch.LongTensor | None = None"}, {"name": "video_grid_thw", "val": ": torch.LongTensor | None = None"}, {"name": "mm_token_type_ids", "val": ": torch.IntTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.5.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.5.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.5.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **past_key_values** (`~cache_utils.Cache`, *optional*) -- Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Only [Cache](/docs/transformers/v5.5.0/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.5.0/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default. The model will output the same cache format that is fed as input. If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. - **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. - **pixel_values** (`torch.Tensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using `image_processor_class`. See `image_processor_class.__call__` for details (`processor_class` uses `image_processor_class` for processing images). - **pixel_values_videos** (`torch.FloatTensor` of shape `(batch_size, num_frames, num_channels, frame_size, frame_size)`, *optional*) -- The tensors corresponding to the input video. Pixel values for videos can be obtained using `video_processor_class`. See `video_processor_class.__call__` for details (`processor_class` uses `video_processor_class` for processing videos). - **image_grid_thw** (`torch.LongTensor` of shape `(num_images, 3)`, *optional*) -- The temporal, height and width of feature shape of each image in LLM. - **video_grid_thw** (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*) -- The temporal, height and width of feature shape of each video in LLM. - **mm_token_type_ids** (`torch.IntTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens matching each modality. For example text (0), image (1), video (2). Multimodal token type ids can be obtained using [AutoProcessor](/docs/transformers/v5.5.0/en/model_doc/auto#transformers.AutoProcessor). See [ProcessorMixin.__call__()](/docs/transformers/v5.5.0/en/model_doc/align#transformers.AlignProcessor.__call__) for details.0`Qwen3VLModelOutputWithPast` or `tuple(torch.FloatTensor)`A `Qwen3VLModelOutputWithPast` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration (`None`) and inputs. The [Qwen3VLModel](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*, defaults to `None`) -- Sequence of hidden-states at the output of the last layer of the model. - **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.5.0/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. - **hidden_states** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple[torch.FloatTensor]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **rope_deltas** (`torch.LongTensor` of shape `(batch_size, )`, *optional*) -- The rope index difference between sequence length and multimodal rope. **Parameters:** config ([Qwen3VLModel](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLModel)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.5.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``Qwen3VLModelOutputWithPast` or `tuple(torch.FloatTensor)`` A `Qwen3VLModelOutputWithPast` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration (`None`) and inputs. #### get_video_features[[transformers.Qwen3VLModel.get_video_features]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L1124) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`, *optional*) -- Last layer hidden-state after a pooling operation on the spatial dimensions. - **hidden_states** (`tuple[torch.FloatTensor, ...]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple[torch.FloatTensor, ...]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **deepstack_features** (`List[torch.FloatTensor]`, *optional*) -- List of hidden-states (feature maps) from deepstack layers. **Parameters:** pixel_values_videos (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input videos. video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*) : The temporal, height and width of feature shape of each video in LLM. **Returns:** ``BaseModelOutputWithDeepstackFeatures` or `tuple(torch.FloatTensor)`` A `BaseModelOutputWithDeepstackFeatures` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Qwen3VLConfig](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLConfig)) and inputs. #### get_image_features[[transformers.Qwen3VLModel.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L1141) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`, *optional*) -- Last layer hidden-state after a pooling operation on the spatial dimensions. - **hidden_states** (`tuple[torch.FloatTensor, ...]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple[torch.FloatTensor, ...]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **deepstack_features** (`List[torch.FloatTensor]`, *optional*) -- List of hidden-states (feature maps) from deepstack layers. **Parameters:** pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input images. image_grid_thw (`torch.LongTensor` of shape `(num_images, 3)`, *optional*) : The temporal, height and width of feature shape of each image in LLM. **Returns:** ``BaseModelOutputWithDeepstackFeatures` or `tuple(torch.FloatTensor)`` A `BaseModelOutputWithDeepstackFeatures` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Qwen3VLConfig](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLConfig)) and inputs. ## Qwen3VLForConditionalGeneration[[transformers.Qwen3VLForConditionalGeneration]] #### transformers.Qwen3VLForConditionalGeneration[[transformers.Qwen3VLForConditionalGeneration]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L1392) forwardtransformers.Qwen3VLForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L1443[{"name": "input_ids", "val": ": LongTensor = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.Tensor | None = None"}, {"name": "pixel_values_videos", "val": ": torch.FloatTensor | None = None"}, {"name": "image_grid_thw", "val": ": torch.LongTensor | None = None"}, {"name": "video_grid_thw", "val": ": torch.LongTensor | None = None"}, {"name": "mm_token_type_ids", "val": ": torch.IntTensor | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}] labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing the masked language modeling loss. Indices should either be in `[0, ..., config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. image_grid_thw (`torch.LongTensor` of shape `(num_images, 3)`, *optional*): The temporal, height and width of feature shape of each image in LLM. video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*): The temporal, height and width of feature shape of each video in LLM. Example: ```python >>> from transformers import AutoProcessor, Qwen3VLForConditionalGeneration >>> model = Qwen3VLForConditionalGeneration.from_pretrained("Qwen/Qwen3-VL-8B-Instruct") >>> processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-8B-Instruct") >>> messages = [ { "role": "user", "content": [ { "type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg", }, {"type": "text", "text": "Describe the image."}, ], } ] >>> inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt" ) >>> # Generate >>> generated_ids = model.generate(**inputs, max_new_tokens=1024) >>> generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)] >>> output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] >>> print(output_text) ``` #### get_video_features[[transformers.Qwen3VLForConditionalGeneration.get_video_features]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L1411) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`, *optional*) -- Last layer hidden-state after a pooling operation on the spatial dimensions. - **hidden_states** (`tuple[torch.FloatTensor, ...]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple[torch.FloatTensor, ...]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **deepstack_features** (`List[torch.FloatTensor]`, *optional*) -- List of hidden-states (feature maps) from deepstack layers. Example: ```python >>> from PIL import Image >>> from transformers import AutoProcessor, Qwen3VLForConditionalGeneration >>> model = Qwen3VLForConditionalGeneration.from_pretrained("Qwen/Qwen3-VL-4B-Instruct") >>> processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-4B-Instruct") >>> messages = [ ... { ... "role": "user", "content": [ ... {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"}, ... {"type": "text", "text": "Where is the cat standing?"}, ... ] ... }, ... ] >>> inputs = processor.apply_chat_template( ... messages, ... tokenize=True, ... return_dict=True, ... return_tensors="pt", ... add_generation_prompt=True ... ) >>> # Generate >>> generate_ids = model.generate(**inputs) >>> processor.batch_decode(generate_ids, skip_special_tokens=True)[0] ``` **Parameters:** pixel_values_videos (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input videos. video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*) : The temporal, height and width of feature shape of each video in LLM. **Returns:** ``BaseModelOutputWithDeepstackFeatures` or `tuple(torch.FloatTensor)`` A `BaseModelOutputWithDeepstackFeatures` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Qwen3VLConfig](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLConfig)) and inputs. #### get_image_features[[transformers.Qwen3VLForConditionalGeneration.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.5.0/src/transformers/models/qwen3_vl/modeling_qwen3_vl.py#L1428) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`, *optional*) -- Last layer hidden-state after a pooling operation on the spatial dimensions. - **hidden_states** (`tuple[torch.FloatTensor, ...]`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple[torch.FloatTensor, ...]`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **deepstack_features** (`List[torch.FloatTensor]`, *optional*) -- List of hidden-states (feature maps) from deepstack layers. Example: ```python >>> from PIL import Image >>> from transformers import AutoProcessor, Qwen3VLForConditionalGeneration >>> model = Qwen3VLForConditionalGeneration.from_pretrained("Qwen/Qwen3-VL-4B-Instruct") >>> processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-4B-Instruct") >>> messages = [ ... { ... "role": "user", "content": [ ... {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"}, ... {"type": "text", "text": "Where is the cat standing?"}, ... ] ... }, ... ] >>> inputs = processor.apply_chat_template( ... messages, ... tokenize=True, ... return_dict=True, ... return_tensors="pt", ... add_generation_prompt=True ... ) >>> # Generate >>> generate_ids = model.generate(**inputs) >>> processor.batch_decode(generate_ids, skip_special_tokens=True)[0] ``` **Parameters:** pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input images. image_grid_thw (`torch.LongTensor` of shape `(num_images, 3)`, *optional*) : The temporal, height and width of feature shape of each image in LLM. **Returns:** ``BaseModelOutputWithDeepstackFeatures` or `tuple(torch.FloatTensor)`` A `BaseModelOutputWithDeepstackFeatures` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([Qwen3VLConfig](/docs/transformers/v5.5.0/en/model_doc/qwen3_vl#transformers.Qwen3VLConfig)) and inputs.