Hugging Face's logo

Transformers documentation

Qwen3.5

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.13.0).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

This model was contributed to Hugging Face Transformers on 2026-02-09.

FlashAttention SDPA

Qwen3.5

Qwen3.5 is Qwen’s natively multimodal foundation model family, trained from scratch on interleaved text, image, and video tokens. It uses a 3:1 hybrid attention stack — three Gated DeltaNet (linear attention) layers for every one Gated Attention (full attention) layer — so long context and vision tokens can be served without paying full quadratic cost on every block.

This page covers the dense Qwen3.5 and Qwen3.6 variants (Qwen/Qwen3.5-9B, Qwen/Qwen3.5-27B, Qwen/Qwen3.6-27B). Qwen3.6 checkpoints share the same architecture and model_type as Qwen3.5 and are loaded with the same classes. For the sparse mixture-of-experts variants see Qwen3.5 MoE. The text backbone reuses Qwen3-Next’s linear-attention decoder with a three-component multimodal RoPE; the vision tower reuses the Qwen3-VL encoder.

You can find all the official Qwen3.5 checkpoints under the Qwen organization.

Quickstart

Pipeline
AutoModel
import torch
from transformers import pipeline

pipe = pipeline(
    task="text-generation",
    model="Qwen/Qwen3.5-9B",
    device_map="auto",
)
print(pipe("The capital of France is", max_new_tokens=20)[0]["generated_text"])

Usage tips and notes

  • Layers are hybrid: Qwen3_5TextConfig’s layer_types is a per-layer list of "linear_attention" or "full_attention" that encodes the 3:1 Gated DeltaNet / Gated Attention stack. The DeltaNet path (Qwen3NextGatedDeltaNet) needs the optional causal_conv1d (from Dao-AILab) and fla packages for its fast kernels — without them, the model silently falls back to slower and more memory hungry PyTorch ops.

  • On NVIDIA GB10 (compute capability 12.1 / SM121) neither causal_conv1d nor fla ship an SM121 build, so the DeltaNet path always falls back to the slow PyTorch reference. Passing use_kernels=True (pip install -U kernels) to from_pretrained() swaps the Gated DeltaNet conv1d and delta-rule cores for a compute-capability-gated Hub kernel (Atlas-Inference/gdn); every other GPU keeps the existing path. The kernel is numerically faithful to the fallback (identical greedy output) and speeds up prefill. Measured on Qwen/Qwen3.6-27B (bf16, GB10/SM121, 1024-token prompt, greedy decode of 256 tokens):

    use_kernelsTTFT (prefill)Decode
    False (PyTorch fallback)1.66 s4.11 tok/s
    True (Atlas-Inference/gdn)1.11 s (1.49x faster)4.14 tok/s

    Decode is unchanged because the single-token DeltaNet recurrence is memory-bandwidth-bound; the win is on the chunked-prefill core and grows with prompt length. Loading the mapped kernel currently requires trust_remote_code=True until Atlas-Inference is added to the trusted-kernels allowlist.

  • Multimodal RoPE splits the head dimension into three components (temporal, height, width) via mrope_section on the text config. If you replace the rotary module, preserve this split or position encodings for image and video tokens will be misaligned.

  • Use Qwen3_5ForCausalLM for text-only generation with Qwen3_5TextConfig; use Qwen3_5ForConditionalGeneration with the full Qwen3_5Config and a processor (from_pretrained()) to feed interleaved image/video + text via apply_chat_template().

Qwen3_5Config

class transformers.Qwen3_5Config

< >

( transformers_version: str | None = Nonearchitectures: list[str] | None = Noneoutput_hidden_states: bool | None = Falsereturn_dict: bool | None = Truedtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = Nonechunk_size_feed_forward: int = 0is_encoder_decoder: bool = Falseid2label: dict[int, str] | dict[str, str] | None = Nonelabel2id: dict[str, int] | dict[str, str] | None = Noneproblem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = Nonetext_config: dict | transformers.configuration_utils.PreTrainedConfig | None = Nonevision_config: dict | transformers.configuration_utils.PreTrainedConfig | None = Noneimage_token_id: int = 248056video_token_id: int = 248057vision_start_token_id: int = 248053vision_end_token_id: int = 248054tie_word_embeddings: bool = False )

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 248056) — The image token index used as a placeholder for input images.
  • video_token_id (int, optional, defaults to 248057) — The video token index used as a placeholder for input videos.
  • vision_start_token_id (int, optional, defaults to 248053) — Token ID that marks the start of a visual segment in the multimodal input sequence.
  • vision_end_token_id (int, optional, defaults to 248054) — 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.

This is the configuration class to store the configuration of a Qwen3_5Model. It is used to instantiate a Qwen3 5 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/Qwen3.5-27B

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

Example:

>>> from transformers import Qwen3_5ForConditionalGeneration, Qwen3_5Config

>>> # Initializing a Qwen3.5 style configuration
>>> configuration = Qwen3_5Config()

>>> # Initializing a model from the Qwen3.5-9B style configuration
>>> model = Qwen3_5ForConditionalGeneration(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

Qwen3_5TextConfig

class transformers.Qwen3_5TextConfig

< >

( transformers_version: str | None = Nonearchitectures: list[str] | None = Noneoutput_hidden_states: bool | None = Falsereturn_dict: bool | None = Truedtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = Nonechunk_size_feed_forward: int = 0is_encoder_decoder: bool = Falseid2label: dict[int, str] | dict[str, str] | None = Nonelabel2id: dict[str, int] | dict[str, str] | None = Noneproblem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = Nonevocab_size: int = 248320hidden_size: int = 4096intermediate_size: int = 12288num_hidden_layers: int = 32num_attention_heads: int = 16num_key_value_heads: int = 4hidden_act: str = 'silu'max_position_embeddings: int = 32768initializer_range: float = 0.02rms_norm_eps: float = 1e-06use_cache: bool = Truetie_word_embeddings: bool = Falserope_parameters: transformers.modeling_rope_utils.RopeParameters | dict | None = Noneattention_bias: bool = Falseattention_dropout: float | int = 0.0head_dim: int = 256linear_conv_kernel_dim: int = 4linear_key_head_dim: int = 128linear_value_head_dim: int = 128linear_num_key_heads: int = 16linear_num_value_heads: int = 32layer_types: list[str] | None = Nonepad_token_id: int | None = Nonebos_token_id: int | None = Noneeos_token_id: int | list[int] | None = None )

Parameters

  • vocab_size (int, optional, defaults to 248320) — 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 12288) — 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 16) — Number of attention heads for each attention layer in the Transformer decoder.
  • num_key_value_heads (int, optional, defaults to 4) — 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. If it is not specified, will default to 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 32768) — 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.
  • tie_word_embeddings (bool, optional, defaults to False) — Whether to tie weight embeddings according to model’s tied_weights_keys mapping.
  • 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.
  • head_dim (int, optional, defaults to 256) — The attention head dimension. If None, it will default to hidden_size // num_attention_heads
  • linear_conv_kernel_dim (int, optional, defaults to 4) — Kernel size of the convolution used in linear attention layers.
  • linear_key_head_dim (int, optional, defaults to 128) — Dimension of each key head in linear attention.
  • linear_value_head_dim (int, optional, defaults to 128) — Dimension of each value head in linear attention.
  • linear_num_key_heads (int, optional, defaults to 16) — Number of key heads used in linear attention layers.
  • linear_num_value_heads (int, optional, defaults to 32) — Number of value heads used in linear attention layers.
  • layer_types (list[str], optional) — A list that explicitly maps each layer index with its layer type. If not provided, it will be automatically generated based on config values.
  • pad_token_id (int, optional) — Token id used for padding in the vocabulary.
  • bos_token_id (int, optional) — Token id used for beginning-of-stream in the vocabulary.
  • eos_token_id (Union[int, list[int]], optional) — Token id used for end-of-stream in the vocabulary.

This is the configuration class to store the configuration of a Qwen3_5Model. It is used to instantiate a Qwen3 5 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/Qwen3.5-27B

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

>>> from transformers import Qwen3_5TextModel, Qwen3_5TextConfig

>>> # Initializing a Qwen3.5 style configuration
>>> configuration =  Qwen3_5TextConfig()

>>> # Initializing a model from the Qwen3.5-9B style configuration
>>> model = Qwen3_5TextModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

Qwen3_5VisionConfig

class transformers.Qwen3_5VisionConfig

< >

( transformers_version: str | None = Nonearchitectures: list[str] | None = Noneoutput_hidden_states: bool | None = Falsereturn_dict: bool | None = Truedtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = Nonechunk_size_feed_forward: int = 0is_encoder_decoder: bool = Falseid2label: dict[int, str] | dict[str, str] | None = Nonelabel2id: dict[str, int] | dict[str, str] | None = Noneproblem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = Nonedepth: int = 27hidden_size: int = 1152hidden_act: str = 'gelu_pytorch_tanh'intermediate_size: int = 4304num_heads: int = 16in_channels: int = 3patch_size: int | list[int] | tuple[int, int] = 16spatial_merge_size: int = 2temporal_patch_size: int | list[int] | tuple[int, int] = 2out_hidden_size: int = 3584num_position_embeddings: int = 2304initializer_range: float = 0.02 )

Parameters

  • depth (int, optional, defaults to 27) — Number of Transformer layers in the vision encoder.
  • hidden_size (int, optional, defaults to 1152) — Dimension of the hidden representations.
  • hidden_act (str, optional, defaults to gelu_pytorch_tanh) — The non-linear activation function (function or string) in the decoder. For example, "gelu", "relu", "silu", etc.
  • intermediate_size (int, optional, defaults to 4304) — Dimension of the MLP representations.
  • num_heads (int, optional, defaults to 16) — Number of attention heads for each attention layer in the Transformer decoder.
  • in_channels (int, optional, defaults to 3) — The number of input channels.
  • patch_size (Union[int, list[int], tuple[int, int]], optional, defaults to 16) — The size (resolution) of each patch.
  • spatial_merge_size (int, optional, defaults to 2) — The size of the spatial merge window used to reduce the number of visual tokens by merging neighboring patches.
  • temporal_patch_size (Union[int, list[int], tuple[int, int]], optional, defaults to 2) — Temporal patch size used in the 3D patch embedding for video inputs.
  • out_hidden_size (int, optional, defaults to 3584) — The output hidden size of the vision model.
  • num_position_embeddings (int, optional, defaults to 2304) — 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.

This is the configuration class to store the configuration of a Qwen3_5Model. It is used to instantiate a Qwen3 5 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/Qwen3.5-27B

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

Qwen3_5Tokenizer

class transformers.Qwen3_5Tokenizer

< >

( vocab: str | dict[str, int] | None = Nonemerges: str | list[str] | None = Nonevocab_file = Nonemerges_file = Noneunk_token: str = '<|endoftext|>'bos_token = Noneeos_token: str = '<|endoftext|>'pad_token: str = '<|endoftext|>'add_prefix_space = None**kwargs )

Qwen3_5VisionModel

class transformers.Qwen3_5VisionModel

< >

( config*inputs**kwargs )

forward

< >

( hidden_states: Tensorgrid_thw: Tensor**kwargs ) → torch.Tensor

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.

Qwen3_5TextModel

class transformers.Qwen3_5TextModel

< >

( config: Qwen3_5TextConfig )

forward

< >

( input_ids: torch.LongTensor | None = Noneattention_mask: torch.Tensor | None = Noneposition_ids: torch.LongTensor | None = Nonepast_key_values: transformers.cache_utils.Cache | None = Noneinputs_embeds: torch.FloatTensor | None = Noneuse_cache: bool | None = None**kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → BaseModelOutputWithPast or tuple(torch.FloatTensor)

Parameters

  • 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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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?

  • 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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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).

Returns

BaseModelOutputWithPast or tuple(torch.FloatTensor)

A 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 (Qwen3_5Config) and inputs.

The Qwen3_5TextModel 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 instance. For more details, see our kv cache guide.

    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.

Qwen3_5Model

class transformers.Qwen3_5Model

< >

( config )

Parameters

  • config (Qwen3_5Model) — 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() method to load the model weights.

The bare Qwen3 5 Model outputting raw hidden-states without any specific head on top.

This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: LongTensor = Noneattention_mask: torch.Tensor | None = Noneposition_ids: torch.LongTensor | None = Nonepast_key_values: transformers.cache_utils.Cache | None = Noneinputs_embeds: torch.FloatTensor | None = Nonepixel_values: torch.Tensor | None = Nonepixel_values_videos: torch.FloatTensor | None = Noneimage_grid_thw: torch.LongTensor | None = Nonevideo_grid_thw: torch.LongTensor | None = Nonemm_token_type_ids: torch.IntTensor | None = None**kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → Qwen3_5ModelOutputWithPast or tuple(torch.FloatTensor)

Parameters

  • 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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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?

  • 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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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. See ProcessorMixin.call() for details.

Returns

Qwen3_5ModelOutputWithPast or tuple(torch.FloatTensor)

A Qwen3_5ModelOutputWithPast 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 Qwen3_5Model 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 instance. For more details, see our kv cache guide.

    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.

  • rope_deltas (torch.LongTensor of shape (batch_size, ), optional) — The rope index difference between sequence length and multimodal rope. The attribute is deprecated and will be removed in v5.20, use model.base_model.rope_deltas instead.

Qwen3_5ForCausalLM

class transformers.Qwen3_5ForCausalLM

< >

( config )

Parameters

  • config (Qwen3_5ForCausalLM) — 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() method to load the model weights.

The Qwen3 5 Model for causal language modeling.

This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_ids: torch.LongTensor | None = Noneattention_mask: torch.Tensor | None = Noneposition_ids: torch.LongTensor | None = Nonepast_key_values: transformers.cache_utils.Cache | None = Noneinputs_embeds: torch.FloatTensor | None = Nonelabels: torch.LongTensor | None = Noneuse_cache: bool | None = Nonelogits_to_keep: int | torch.Tensor = 0**kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → CausalLMOutputWithPast or tuple(torch.FloatTensor)

Parameters

  • 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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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?

  • 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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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.
  • 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].
  • 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).
  • logits_to_keep (Union[int, torch.Tensor], optional, defaults to 0) — If an int, compute logits for the last logits_to_keep tokens. If 0, calculate logits for all input_ids (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size. If a torch.Tensor, must be 1D corresponding to the indices to keep in the sequence length dimension. This is useful when using packed tensor format (single dimension for batch and sequence length).

Returns

CausalLMOutputWithPast or tuple(torch.FloatTensor)

A CausalLMOutputWithPast 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 (Qwen3_5Config) and inputs.

The Qwen3_5ForCausalLM 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.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Language modeling loss (for next-token prediction).

  • logits (torch.FloatTensor of shape (batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

  • past_key_values (Cache, optional, returned when use_cache=True is passed or when config.use_cache=True) — It is a Cache instance. For more details, see our kv cache guide.

    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.

Example:

>>> from transformers import AutoTokenizer, Qwen3_5ForCausalLM

>>> model = Qwen3_5ForCausalLM.from_pretrained("Qwen/Qwen3_5-8B")
>>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3_5-8B")

>>> prompt = "Hey, are you conscious? Can you talk to me?"
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> # Generate
>>> generate_ids = model.generate(inputs.input_ids, max_length=30)
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."

Qwen3_5ForConditionalGeneration

class transformers.Qwen3_5ForConditionalGeneration

< >

( config )

forward

< >

( input_ids: LongTensor = Noneattention_mask: torch.Tensor | None = Noneposition_ids: torch.LongTensor | None = Nonepast_key_values: transformers.cache_utils.Cache | None = Noneinputs_embeds: torch.FloatTensor | None = Nonelabels: torch.LongTensor | None = Nonepixel_values: torch.Tensor | None = Nonepixel_values_videos: torch.FloatTensor | None = Noneimage_grid_thw: torch.LongTensor | None = Nonevideo_grid_thw: torch.LongTensor | None = Nonemm_token_type_ids: torch.IntTensor | None = Nonelogits_to_keep: int | torch.Tensor = 0**kwargs: 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:

>>> from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration

>>> model = Qwen3_5ForConditionalGeneration.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)

Qwen3_5ForSequenceClassification

class transformers.Qwen3_5ForSequenceClassification

< >

( config )

forward

< >

( input_ids: LongTensor = Noneattention_mask: torch.Tensor | None = Noneposition_ids: torch.LongTensor | None = Nonepast_key_values: transformers.cache_utils.Cache | None = Noneinputs_embeds: torch.FloatTensor | None = Nonepixel_values: torch.Tensor | None = Nonepixel_values_videos: torch.FloatTensor | None = Noneimage_grid_thw: torch.LongTensor | None = Nonevideo_grid_thw: torch.LongTensor | None = Nonemm_token_type_ids: torch.IntTensor | None = None**kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] )

Qwen3_5TextForSequenceClassification

class transformers.Qwen3_5TextForSequenceClassification

< >

( config )

forward

< >

( input_ids: torch.LongTensor | None = Noneattention_mask: torch.Tensor | None = Noneposition_ids: torch.LongTensor | None = Nonepast_key_values: transformers.cache_utils.Cache | None = Noneinputs_embeds: torch.FloatTensor | None = Nonelabels: torch.LongTensor | None = Noneuse_cache: bool | None = None**kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → SequenceClassifierOutputWithPast or tuple(torch.FloatTensor)

Parameters

  • 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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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?

  • 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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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.
  • 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].
  • 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).

Returns

SequenceClassifierOutputWithPast or tuple(torch.FloatTensor)

A SequenceClassifierOutputWithPast 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 GenericForSequenceClassification 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.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.

  • logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).

  • past_key_values (Cache, optional, returned when use_cache=True is passed or when config.use_cache=True) — It is a Cache instance. For more details, see our kv cache guide.

    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.

Qwen3_5ForTokenClassification

class transformers.Qwen3_5ForTokenClassification

< >

( config )

forward

< >

( input_ids: torch.LongTensor | None = Noneattention_mask: torch.Tensor | None = Noneposition_ids: torch.LongTensor | None = Nonepast_key_values: transformers.cache_utils.Cache | None = Noneinputs_embeds: torch.FloatTensor | None = Nonelabels: torch.LongTensor | None = Noneuse_cache: bool | None = None**kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → TokenClassifierOutput or tuple(torch.FloatTensor)

Parameters

  • 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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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?

  • 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 instance is allowed as input, see our kv cache guide. If no past_key_values are passed, 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.
  • 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].
  • 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).

Returns

TokenClassifierOutput or tuple(torch.FloatTensor)

A TokenClassifierOutput 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 GenericForTokenClassification 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.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification loss.

  • logits (torch.FloatTensor of shape (batch_size, sequence_length, config.num_labels)) — Classification scores (before SoftMax).

  • 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.

Qwen3_5Tokenizer

class transformers.Qwen3_5Tokenizer

< >

( vocab: str | dict[str, int] | None = Nonemerges: str | list[str] | None = Nonevocab_file = Nonemerges_file = Noneunk_token: str = '<|endoftext|>'bos_token = Noneeos_token: str = '<|endoftext|>'pad_token: str = '<|endoftext|>'add_prefix_space = None**kwargs )

Update on GitHub

←Qwen3 Qwen3.5 Moe→