Transformers documentation
Overview
Overview
The Qwen3-Next series represents our next-generation foundation models, optimized for extreme context length and large-scale parameter efficiency. The series introduces a suite of architectural innovations designed to maximize performance while minimizing computational cost:
- Hybrid Attention: Replaces standard attention with the combination of Gated DeltaNet and Gated Attention, enabling efficient context modeling.
- High-Sparsity MoE: Achieves an extreme low activation ratio as 1:50 in MoE layers — drastically reducing FLOPs per token while preserving model capacity.
- Multi-Token Prediction(MTP): Boosts pretraining model performance, and accelerates inference.
- Other Optimizations: Includes techniques such as zero-centered and weight-decayed layernorm, Gated Attention, and other stabilizing enhancements for robust training.
Built on this architecture, we trained and open-sourced Qwen3-Next-80B-A3B — 80B total parameters, only 3B active — achieving extreme sparsity and efficiency.
Despite its ultra-efficiency, it outperforms Qwen3-32B on downstream tasks — while requiring less than 1/10 of the training cost. Moreover, it delivers over 10x higher inference throughput than Qwen3-32B when handling contexts longer than 32K tokens.
For more details, please visit our blog Qwen3-Next (blog post).
Usage examples
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen3-Next-80B-A3B-Instruct"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
dtype="auto",
device_map="auto"
)
# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
content = tokenizer.decode(output_ids, skip_special_tokens=True)
print("content:", content)Qwen3NextConfig
class transformers.Qwen3NextConfig
< source >( vocab_size = 151936 hidden_size = 2048 intermediate_size = 5632 num_hidden_layers = 48 num_attention_heads = 16 num_key_value_heads = 2 hidden_act = 'silu' max_position_embeddings = 32768 initializer_range = 0.02 rms_norm_eps = 1e-06 use_cache = True tie_word_embeddings = False rope_theta = 10000.0 rope_scaling = None partial_rotary_factor = 0.25 attention_bias = False attention_dropout = 0.0 head_dim = 256 linear_conv_kernel_dim = 4 linear_key_head_dim = 128 linear_value_head_dim = 128 linear_num_key_heads = 16 linear_num_value_heads = 32 decoder_sparse_step = 1 moe_intermediate_size = 512 shared_expert_intermediate_size = 512 num_experts_per_tok = 10 num_experts = 512 norm_topk_prob = True output_router_logits = False router_aux_loss_coef = 0.001 mlp_only_layers = [] layer_types = None **kwargs )
Parameters
- vocab_size (
int, optional, defaults to 151936) — Vocabulary size of the model. Defines the number of different tokens that can be represented by theinputs_ids. - hidden_size (
int, optional, defaults to 2048) — Dimension of the hidden representations. - intermediate_size (
int, optional, defaults to 5632) — Dimension of the MLP representations. - num_hidden_layers (
int, optional, defaults to 48) — Number of hidden layers in the Transformer encoder. - num_attention_heads (
int, optional, defaults to 16) — Number of attention heads for each attention layer in the Transformer encoder. - num_key_value_heads (
int, optional, defaults to 2) — This is the number of key_value heads that should be used to implement Grouped Query Attention. Ifnum_key_value_heads=num_attention_heads, the model will use Multi Head Attention (MHA), ifnum_key_value_heads=1the 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 checkout this paper. If it is not specified, will default to32. - hidden_act (
str, optional, defaults to"silu") — The non-linear activation function in the decoder. - 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 toTrue) — Whether or not the model should return the last key/values attentions (not used by all models). Only relevant ifconfig.is_decoder=True. - tie_word_embeddings (
bool, optional, defaults toFalse) — Whether the model’s input and output word embeddings should be tied. - rope_theta (
float, optional, defaults to 10000.0) — The base period of the RoPE embeddings. - rope_scaling (
Dict, optional) — Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longermax_position_embeddings, we recommend you to update this value accordingly. Expected contents:rope_type(str): The sub-variant of RoPE to use. Can be one of [‘default’, ‘linear’, ‘dynamic’, ‘yarn’, ‘longrope’, ‘llama3’], with ‘default’ being the original RoPE implementation.factor(float, optional): Used with all rope types except ‘default’. The scaling factor to apply to the RoPE embeddings. In most scaling types, afactorof x will enable the model to handle sequences of length x original maximum pre-trained length.original_max_position_embeddings(int, optional): Used with ‘dynamic’, ‘longrope’ and ‘llama3’. The original max position embeddings used during pretraining.attention_factor(float, optional): Used with ‘yarn’ and ‘longrope’. The scaling factor to be applied on the attention computation. If unspecified, it defaults to value recommended by the implementation, using thefactorfield to infer the suggested value.beta_fast(float, optional): Only used with ‘yarn’. Parameter to set the boundary for extrapolation (only) in the linear ramp function. If unspecified, it defaults to 32.beta_slow(float, optional): Only used with ‘yarn’. Parameter to set the boundary for interpolation (only) in the linear ramp function. If unspecified, it defaults to 1.short_factor(List[float], optional): Only used with ‘longrope’. The scaling factor to be applied to short contexts (<original_max_position_embeddings). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2long_factor(List[float], optional): Only used with ‘longrope’. The scaling factor to be applied to long contexts (<original_max_position_embeddings). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2low_freq_factor(float, optional): Only used with ‘llama3’. Scaling factor applied to low frequency components of the RoPEhigh_freq_factor(float, optional*): Only used with ‘llama3’. Scaling factor applied to high frequency components of the RoPE - partial_rotary_factor (
float, optional, defaults to 0.25) — Percentage of the query and keys which will have rotary embedding. - attention_bias (
bool, optional, defaults toFalse) — Whether to use a bias in the query, key, value and output projection layers during self-attention. - attention_dropout (
float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities. - head_dim (
int, optional, defaults to 256) — Projection weights dimension in multi-head attention. - 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. - decoder_sparse_step (
int, optional, defaults to 1) — The frequency of the MoE layer. - moe_intermediate_size (
int, optional, defaults to 512) — Intermediate size of the routed expert. - shared_expert_intermediate_size (
int, optional, defaults to 512) — Intermediate size of the shared expert. - num_experts_per_tok (
int, optional, defaults to 10) — Number of selected experts. - num_experts (
int, optional, defaults to 512) — Number of routed experts. - norm_topk_prob (
bool, optional, defaults toTrue) — Whether to normalize the topk probabilities. - output_router_logits (
bool, optional, defaults toFalse) — Whether or not the router logits should be returned by the model. Enabling this will also allow the model to output the auxiliary loss, including load balancing loss and router z-loss. - router_aux_loss_coef (
float, optional, defaults to 0.001) — The aux loss factor for the total loss. - mlp_only_layers (
list[int], optional, defaults to[]) — Indicate which layers use Qwen3NextMLP rather than Qwen3NextSparseMoeBlock The list contains layer index, from 0 to num_layers-1 if we have num_layers layers Ifmlp_only_layersis empty,decoder_sparse_stepis used to determine the sparsity. - layer_types (
list[str], optional) — Types of each layer (attention or linear).
This is the configuration class to store the configuration of a Qwen3NextModel. It is used to instantiate a Qwen3-Next model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of Qwen3-Next-80B-A3B-Instruct Qwen/Qwen3-Next-80B-A3B-Instruct.
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 Qwen3NextModel, Qwen3NextConfig
>>> # Initializing a Qwen3Next style configuration
>>> configuration = Qwen3NextConfig()
>>> # Initializing a model from the Qwen3-Next-80B-A3B style configuration
>>> model = Qwen3NextModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.configQwen3NextModel
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.cache_utils.Cache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None use_cache: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.MoeModelOutputWithPast or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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.
- attention_mask (
torch.Tensorof 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.
- position_ids (
torch.LongTensorof 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]. - 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 thepast_key_valuesreturned by the model at a previous stage of decoding, whenuse_cache=Trueorconfig.use_cache=True.Only Cache instance is allowed as input, see our kv cache guide. If no
past_key_valuesare passed, DynamicCache will be initialized by default.The model will output the same cache format that is fed as input.
If
past_key_valuesare used, the user is expected to input only unprocessedinput_ids(those that don’t have their past key value states given to this model) of shape(batch_size, unprocessed_length)instead of allinput_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - cache_position (
torch.LongTensorof shape(sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily toposition_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.
Returns
transformers.modeling_outputs.MoeModelOutputWithPast or tuple(torch.FloatTensor)
A transformers.modeling_outputs.MoeModelOutputWithPast 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 (Qwen3NextConfig) and inputs.
-
last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model. -
past_key_values (
Cache, optional, returned whenuse_cache=Trueis passed or whenconfig.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=Truein the cross-attention blocks) that can be used (seepast_key_valuesinput) to speed up sequential decoding. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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.
-
router_logits (
tuple(torch.FloatTensor), optional, returned whenoutput_router_probs=Trueandconfig.add_router_probs=Trueis passed or whenconfig.output_router_probs=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, sequence_length, num_experts).Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary loss for Mixture of Experts models.
The Qwen3NextModel 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.
Qwen3NextForCausalLM
class transformers.Qwen3NextForCausalLM
< source >( config )
Parameters
- config (Qwen3NextForCausalLM) — 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 Next 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
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.models.qwen3_next.modeling_qwen3_next.Qwen3NextDynamicCache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_router_logits: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None logits_to_keep: typing.Union[int, torch.Tensor] = 0 **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.MoeCausalLMOutputWithPast or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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.
- attention_mask (
torch.Tensorof 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.
- position_ids (
torch.LongTensorof 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]. - past_key_values (
~models.qwen3_next.modeling_qwen3_next.Qwen3NextDynamicCache, 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 thepast_key_valuesreturned by the model at a previous stage of decoding, whenuse_cache=Trueorconfig.use_cache=True.Only Cache instance is allowed as input, see our kv cache guide. If no
past_key_valuesare passed, DynamicCache will be initialized by default.The model will output the same cache format that is fed as input.
If
past_key_valuesare used, the user is expected to input only unprocessedinput_ids(those that don’t have their past key value states given to this model) of shape(batch_size, unprocessed_length)instead of allinput_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - labels (
torch.LongTensorof 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 (seeinput_idsdocstring). Tokens with indices set to-100are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size]. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - output_router_logits (
bool, optional) — Whether or not to return the logits of all the routers. They are useful for computing the router loss, and should not be returned during inference. - cache_position (
torch.LongTensorof shape(sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily toposition_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length. - logits_to_keep (
Union[int, torch.Tensor], defaults to0) — If anint, compute logits for the lastlogits_to_keeptokens. If0, calculate logits for allinput_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 atorch.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
transformers.modeling_outputs.MoeCausalLMOutputWithPast or tuple(torch.FloatTensor)
A transformers.modeling_outputs.MoeCausalLMOutputWithPast 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 (Qwen3NextConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss (for next-token prediction). -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
aux_loss (
torch.FloatTensor, optional, returned whenlabelsis provided) — aux_loss for the sparse modules. -
router_logits (
tuple(torch.FloatTensor), optional, returned whenoutput_router_probs=Trueandconfig.add_router_probs=Trueis passed or whenconfig.output_router_probs=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, sequence_length, num_experts).Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary loss for Mixture of Experts models.
-
past_key_values (
Cache, optional, returned whenuse_cache=Trueis passed or whenconfig.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_valuesinput) to speed up sequential decoding. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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.
The Qwen3NextForCausalLM 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.
Example:
>>> from transformers import AutoTokenizer, Qwen3NextForCausalLM
>>> model = Qwen3NextForCausalLM.from_pretrained("Qwen/Qwen3-Next-80B-A3B-Instruct")
>>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Next-80B-A3B-Instruct")
>>> 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."Qwen3NextForSequenceClassification
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.cache_utils.Cache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.SequenceClassifierOutputWithPast or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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.
- attention_mask (
torch.Tensorof 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.
- position_ids (
torch.LongTensorof 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]. - 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 thepast_key_valuesreturned by the model at a previous stage of decoding, whenuse_cache=Trueorconfig.use_cache=True.Only Cache instance is allowed as input, see our kv cache guide. If no
past_key_valuesare passed, DynamicCache will be initialized by default.The model will output the same cache format that is fed as input.
If
past_key_valuesare used, the user is expected to input only unprocessedinput_ids(those that don’t have their past key value states given to this model) of shape(batch_size, unprocessed_length)instead of allinput_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - labels (
torch.LongTensorof 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 (seeinput_idsdocstring). Tokens with indices set to-100are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size]. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values).
Returns
transformers.modeling_outputs.SequenceClassifierOutputWithPast or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). -
past_key_values (
Cache, optional, returned whenuse_cache=Trueis passed or whenconfig.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_valuesinput) to speed up sequential decoding. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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.
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.
Qwen3NextForQuestionAnswering
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.cache_utils.Cache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None start_positions: typing.Optional[torch.LongTensor] = None end_positions: typing.Optional[torch.LongTensor] = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.modeling_outputs.QuestionAnsweringModelOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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.
- attention_mask (
torch.Tensorof 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.
- position_ids (
torch.LongTensorof 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]. - 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 thepast_key_valuesreturned by the model at a previous stage of decoding, whenuse_cache=Trueorconfig.use_cache=True.Only Cache instance is allowed as input, see our kv cache guide. If no
past_key_valuesare passed, DynamicCache will be initialized by default.The model will output the same cache format that is fed as input.
If
past_key_valuesare used, the user is expected to input only unprocessedinput_ids(those that don’t have their past key value states given to this model) of shape(batch_size, unprocessed_length)instead of allinput_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - start_positions (
torch.LongTensorof shape(batch_size,), optional) — Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss. - end_positions (
torch.LongTensorof shape(batch_size,), optional) — Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.
Returns
transformers.modeling_outputs.QuestionAnsweringModelOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.QuestionAnsweringModelOutput 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.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Total span extraction loss is the sum of a Cross-Entropy for the start and end positions. -
start_logits (
torch.FloatTensorof shape(batch_size, sequence_length)) — Span-start scores (before SoftMax). -
end_logits (
torch.FloatTensorof shape(batch_size, sequence_length)) — Span-end scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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.
The GenericForQuestionAnswering 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.
Qwen3NextForTokenClassification
forward
< source >( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[transformers.cache_utils.Cache] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None **kwargs ) → transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof 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.
- attention_mask (
torch.Tensorof 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.
- position_ids (
torch.LongTensorof 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]. - 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 thepast_key_valuesreturned by the model at a previous stage of decoding, whenuse_cache=Trueorconfig.use_cache=True.Only Cache instance is allowed as input, see our kv cache guide. If no
past_key_valuesare passed, DynamicCache will be initialized by default.The model will output the same cache format that is fed as input.
If
past_key_valuesare used, the user is expected to input only unprocessedinput_ids(those that don’t have their past key value states given to this model) of shape(batch_size, unprocessed_length)instead of allinput_idsof shape(batch_size, sequence_length). - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - labels (
torch.LongTensorof 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 (seeinput_idsdocstring). Tokens with indices set to-100are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size]. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values).
Returns
transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification loss. -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.num_labels)) — Classification scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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.
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.