# Switch Transformers

[Switch Transformers](https://huggingface.co/papers/2101.03961) is a sparse T5 model where the MLP layer is replaced by a Mixture-of-Experts (MoE). A routing mechanism associates each token with an expert and each expert is a dense MLP. Sparsity enables better scaling and the routing mechanism allows the model to select relevant weights on the fly which increases model capacity.

You can find all the original Switch Transformers checkpoints under the [Switch Transformer](https://huggingface.co/collections/google/switch-transformers-release-6548c35c6507968374b56d1f) collection.

> [!TIP]
> This model was contributed by [ybelkada](https://huggingface.co/ybelkada) and [ArthurZ](https://huggingface.co/ArthurZ).
>
> Click on the Switch Transformers models in the right sidebar for more examples of how to apply Switch Transformers to different natural language tasks.

The example below demonstrates how to predict the masked token with [Pipeline](/docs/transformers/v5.8.0/en/main_classes/pipelines#transformers.Pipeline), [AutoModel](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoModel), and from the command line.

```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("google/switch-base-8")
model = AutoModelForSeq2SeqLM.from_pretrained("google/switch-base-8", device_map="auto")

input_text = "The capital of France is <extra_id_0>."
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(0)

outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the [Quantization](../quantization/overview) overview for more available quantization backends.

The example below uses [bitsandbytes](../quantization/bitsandbytes/) to only quantize the weights to 8-bits.

```python
# pip install bitsandbytes
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, BitsAndBytesConfig

tokenizer = AutoTokenizer.from_pretrained("google/switch-base-8")
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
model = AutoModelForSeq2SeqLM.from_pretrained("google/switch-base-8", device_map="auto", quantization_config=quantization_config)

input_text = "The capital of France is <extra_id_0>."
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(0)

outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```

## SwitchTransformersConfig[[transformers.SwitchTransformersConfig]]

#### transformers.SwitchTransformersConfig[[transformers.SwitchTransformersConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/configuration_switch_transformers.py#L26)

This is the configuration class to store the configuration of a SwitchTransformersModel. It is used to instantiate a Switch Transformers
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 [google/switch-base-8](https://huggingface.co/google/switch-base-8)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information.

**Parameters:**

is_encoder_decoder (`bool`, *optional*, defaults to `True`) : Whether the model is used as an encoder/decoder or not.

vocab_size (`int`, *optional*, defaults to `32128`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`.

d_model (`int`, *optional*, defaults to `768`) : Size of the encoder layers and the pooler layer.

d_kv (`int`, *optional*, defaults to `64`) : Size of the key, query, value projections per attention head. The `inner_dim` of the projection layer will be defined as `num_heads * d_kv`.

d_ff (`int`, *optional*, defaults to `2048`) : Dimension of the MLP representations.

expert_capacity (`int`, *optional*, defaults to `64`) : The number of tokens that each expert can process. If `None`, `expert_capacity` will be set to `(sequence_length / num_experts) * capacity_factor`.

num_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer decoder.

num_sparse_encoder_layers (`int`, *optional*, defaults to 3) : Number of sparse (MoE) dense hidden layers in the Transformer encoder layer. Note: When set to 0 with `num_layers=1`, the current implementation may still create a sparse layer due to the sparse step calculation. This edge case is not encountered in existing checkpoints.

num_decoder_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set.

num_sparse_decoder_layers (`int`, *optional*, defaults to 3) : Number of sparse (MoE) dense hidden layers in the Transformer decoder layer. Note: When set to 0 with `num_decoder_layers=1`, the current implementation may still create a sparse layer due to the sparse step calculation. This edge case is not encountered in existing checkpoints.

num_heads (`int`, *optional*, defaults to `12`) : Number of attention heads for each attention layer in the Transformer decoder.

num_experts (`int`, *optional*, defaults to `8`) : Number of routed experts in MoE layers. 

router_bias (`bool`, *optional*, defaults to `False`) : Whether to add a bias to the router.

router_jitter_noise (`Union[int, float]`, *optional*, defaults to `0.01`) : Amount of noise to add to the router logits during training for better load balancing.

router_dtype (`str`, *optional*, default to `"float32"`) : The `dtype` used for the routers. It is preferable to keep the `dtype` to `"float32"` as specified in the *selective precision* discussion in [the paper](https://huggingface.co/papers/2101.03961).

router_ignore_padding_tokens (`bool`, *optional*, defaults to `False`) : Whether to ignore padding tokens when routing.

relative_attention_num_buckets (`int`, *optional*, defaults to 32) : The number of buckets to use for each attention layer.

relative_attention_max_distance (`int`, *optional*, defaults to 128) : The maximum distance of the longer sequences for the bucket separation.

dropout_rate (`Union[float, int]`, *optional*, defaults to `0.1`) : The ratio for all dropout layers.

layer_norm_epsilon (`float`, *optional*, defaults to `1e-06`) : The epsilon used by the layer normalization layers.

router_z_loss_coef (`float`, *optional*, defaults to `0.001`) : Coefficient for the router z-loss, which penalizes large router logits to improve training stability.

router_aux_loss_coef (`float`, *optional*, defaults to `0.001`) : Auxiliary load balancing loss coefficient. Used to penalize uneven expert routing in MoE models.

initializer_factor (`float`, *optional*, defaults to `1.0`) : A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing).

dense_act_fn (`string`, *optional*, defaults to `"relu"`) : Type of feed forward layer to be used. Should be one of `"relu"` or `"gated-gelu"`. SwitchTransformersv1.1 uses the `"gated-gelu"` feed forward projection. Original SwitchTransformers uses `"relu"`.

add_router_probs (`bool`, *optional*, defaults to `False`) : Whether to output router probabilities to compute router auxiliary loss.

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.

pad_token_id (`int`, *optional*, defaults to `0`) : Token id used for padding in the vocabulary.

eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `1`) : Token id used for end-of-stream in the vocabulary.

bos_token_id (`int`, *optional*) : Token id used for beginning-of-stream in the vocabulary.

tie_word_embeddings (`bool`, *optional*, defaults to `True`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping.

is_decoder (`bool`, *optional*, defaults to `False`) : Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.

add_cross_attention (`bool`, *optional*, defaults to `False`) : Whether cross-attention layers should be added to the model.

## SwitchTransformersTop1Router[[transformers.SwitchTransformersTop1Router]]

#### transformers.SwitchTransformersTop1Router[[transformers.SwitchTransformersTop1Router]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L51)

Router using tokens choose top-1 experts assignment.

This router uses the same mechanism as in Switch Transformer (https://huggingface.co/papers/2101.03961) and V-MoE
(https://huggingface.co/papers/2106.05974): tokens choose their top experts. Items are sorted by router_probs and then
routed to their choice of expert until the expert's expert_capacity is reached. **There is no guarantee that each
token is processed by an expert**, or that each expert receives at least one token.

forwardtransformers.SwitchTransformersTop1Router.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L71[{"name": "hidden_states", "val": ": Tensor"}]- **hidden_states** (`torch.Tensor`) --
  (batch_size, sequence_length, hidden_dim) from which router probabilities are computed.0router_probabilities (`torch.Tensor`)Tensor of shape (batch_size, sequence_length, num_experts) corresponding to the probabilities for each
token and expert. Used for routing tokens to experts.
router_logits (`torch.Tensor`):
Logits tensor of shape (batch_size, sequence_length, num_experts) corresponding to raw router logits.
This is used later for computing router z-loss.

Computes router probabilities from input hidden states.

**Parameters:**

hidden_states (`torch.Tensor`) : (batch_size, sequence_length, hidden_dim) from which router probabilities are computed.

**Returns:**

`router_probabilities (`torch.Tensor`)`

Tensor of shape (batch_size, sequence_length, num_experts) corresponding to the probabilities for each
token and expert. Used for routing tokens to experts.
router_logits (`torch.Tensor`):
Logits tensor of shape (batch_size, sequence_length, num_experts) corresponding to raw router logits.
This is used later for computing router z-loss.

## SwitchTransformersSparseMLP[[transformers.SwitchTransformersSparseMLP]]

#### transformers.SwitchTransformersSparseMLP[[transformers.SwitchTransformersSparseMLP]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L178)

forwardtransformers.SwitchTransformersSparseMLP.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L184[{"name": "hidden_states", "val": ": Tensor"}]

## SwitchTransformersModel[[transformers.SwitchTransformersModel]]

#### transformers.SwitchTransformersModel[[transformers.SwitchTransformersModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L747)

The bare Switch Transformers Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.SwitchTransformersModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L775[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.BoolTensor | None = None"}, {"name": "encoder_outputs", "val": ": tuple[tuple[torch.FloatTensor]] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.Tensor | 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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` 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)
- **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are decoder input IDs?](../glossary#decoder-input-ids)
- **decoder_attention_mask** (`torch.BoolTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Mask to avoid performing attention on certain token indices. By default, a causal mask will be used, to
  make sure the model can only look at previous inputs in order to predict the future.
- **encoder_outputs** (`tuple[tuple[torch.FloatTensor]]`, *optional*) --
  Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`)
  `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of
  hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
- **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/v5.8.0/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/v5.8.0/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.Tensor` 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.
- **decoder_inputs_embeds** (`torch.Tensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded
  representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be
  input (see `past_key_values`). This is useful if you want more control over how to convert
  `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix.

  If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value
  of `inputs_embeds`.0`Seq2SeqMoEModelOutput` or `tuple(torch.FloatTensor)`A `Seq2SeqMoEModelOutput` 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 [SwitchTransformersModel](/docs/transformers/v5.8.0/en/model_doc/switch_transformers#transformers.SwitchTransformersModel) 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 decoder 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** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [EncoderDecoderCache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.EncoderDecoderCache) 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 in the cross-attention
  blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
- **decoder_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 decoder at the output of each layer plus the optional initial embedding outputs.
- **decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.
- **decoder_router_logits** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_logits=True` is passed or when `config.add_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.

  Router logits of the decoder model, useful to compute the auxiliary loss for Mixture of Experts models.
- **cross_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 of the decoder's cross-attention layer, after the attention softmax, used to compute the
  weighted average in the cross-attention heads.
- **encoder_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 encoder of the model.
- **encoder_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 encoder at the output of each layer plus the optional initial embedding outputs.
- **encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.
- **encoder_router_logits** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_logits=True` is passed or when `config.add_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.

  Router logits of the encoder model, useful to compute the auxiliary loss and the z_loss for the sparse
  modules.

**Parameters:**

config ([SwitchTransformersConfig](/docs/transformers/v5.8.0/en/model_doc/switch_transformers#transformers.SwitchTransformersConfig)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

``Seq2SeqMoEModelOutput` or `tuple(torch.FloatTensor)``

A `Seq2SeqMoEModelOutput` 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.

## SwitchTransformersForConditionalGeneration[[transformers.SwitchTransformersForConditionalGeneration]]

#### transformers.SwitchTransformersForConditionalGeneration[[transformers.SwitchTransformersForConditionalGeneration]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L889)

SWITCH_TRANSFORMERS Model with a `language modeling` head on top.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.SwitchTransformersForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L926[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.BoolTensor | None = None"}, {"name": "encoder_outputs", "val": ": tuple[tuple[torch.Tensor]] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "decoder_inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "output_router_logits", "val": ": bool | None = False"}, {"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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` 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)
- **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are decoder input IDs?](../glossary#decoder-input-ids)
- **decoder_attention_mask** (`torch.BoolTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Mask to avoid performing attention on certain token indices. By default, a causal mask will be used, to
  make sure the model can only look at previous inputs in order to predict the future.
- **encoder_outputs** (`tuple[tuple[torch.Tensor]]`, *optional*) --
  Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`)
  `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of
  hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
- **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/v5.8.0/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/v5.8.0/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.
- **decoder_inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded
  representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be
  input (see `past_key_values`). This is useful if you want more control over how to convert
  `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix.

  If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value
  of `inputs_embeds`.
- **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]`.
- **output_router_logits** (`bool`, *optional*, defaults to `False`) --
  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.0`Seq2SeqMoEOutput` or `tuple(torch.FloatTensor)`A `Seq2SeqMoEOutput` 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 [SwitchTransformersForConditionalGeneration](/docs/transformers/v5.8.0/en/model_doc/switch_transformers#transformers.SwitchTransformersForConditionalGeneration) 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.
- **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** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [EncoderDecoderCache](/docs/transformers/v5.8.0/en/internal/generation_utils#transformers.EncoderDecoderCache) 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 in the cross-attention
  blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
- **decoder_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 decoder at the output of each layer plus the initial embedding outputs.
- **decoder_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 of the decoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.
- **decoder_router_logits** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_logits=True` is passed or when `config.add_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.

  Router logits of the decoder model, useful to compute the auxiliary loss for Mixture of Experts models.
- **cross_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 of the decoder's cross-attention layer, after the attention softmax, used to compute the
  weighted average in the cross-attention heads.
- **encoder_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 encoder of the model.
- **encoder_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 encoder at the output of each layer plus the initial embedding outputs.
- **encoder_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 of the encoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.
- **encoder_router_logits** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_logits=True` is passed or when `config.add_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.

  Router logits of the encoder model, useful to compute the auxiliary loss and z_loss for Mixture of Experts
  models.

**Parameters:**

config ([SwitchTransformersConfig](/docs/transformers/v5.8.0/en/model_doc/switch_transformers#transformers.SwitchTransformersConfig)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

``Seq2SeqMoEOutput` or `tuple(torch.FloatTensor)``

A `Seq2SeqMoEOutput` 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.

## SwitchTransformersEncoderModel[[transformers.SwitchTransformersEncoderModel]]

#### transformers.SwitchTransformersEncoderModel[[transformers.SwitchTransformersEncoderModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L1047)

forwardtransformers.SwitchTransformersEncoderModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/switch_transformers/modeling_switch_transformers.py#L1069[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | 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/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` 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)
- **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`).0`MoEModelOutput` or `tuple(torch.FloatTensor)`A `MoEModelOutput` 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 [SwitchTransformersEncoderModel](/docs/transformers/v5.8.0/en/model_doc/switch_transformers#transformers.SwitchTransformersEncoderModel) 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.
- **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.
- **router_probs** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_probs=True` and `config.add_router_probs=True` is passed or when `config.output_router_probs=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.

  Raw router probabilities that are computed by MoE routers, these terms are used to compute the auxiliary
  loss and the z_loss for Mixture of Experts models.

**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](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.  [What are input IDs?](../glossary#input-ids)

attention_mask (`torch.FloatTensor` 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)

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:**

``MoEModelOutput` or `tuple(torch.FloatTensor)``

A `MoEModelOutput` 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.