# GraniteMoeSWA

GraniteMoeSWA combines the mixture-of-experts (MoE) architecture of [GraniteMoeShared](./granitemoeshared) with the sliding-window attention and learnable attention sinks of [GraniteSWA](./granite_swa):

- **Mixture of experts.** Each block routes every token to a subset of experts (`num_experts_per_tok` of `num_local_experts`). Optional **shared experts** are supported but **disabled by default** (`shared_intermediate_size=0`); set it to a positive value to enable them.
- **Per-layer sliding window attention.** Each layer is either `"full_attention"` or `"sliding_attention"` (configured by `layer_types`). By default every fourth layer (`i % 4 == 0`) keeps full attention and the rest attend only to the most recent `sliding_window` tokens.
- **Learnable per-head attention sinks.** Each head learns a scalar sink that rescales its attention output by `sigmoid(logsumexp(attn_logits) - sink)`, equivalent to appending a single extra learnable logit to the softmax denominator (the attention-sink mechanism used by GPT-OSS).

> [!TIP]
> SDPA is not supported because the attention sink cannot be expressed through `torch.nn.functional.scaled_dot_product_attention`. Supported backends are:
> - **Training + inference:** `"eager"`, `"flex_attention"` (preferred for training)
> - **Inference:** `"flash_attention_3"` (via vLLM FA3 ['hub'](https://github.com/huggingface/kernels) kernel — also the fallback when FlashAttention-3 is not installed but `kernels` is), `"flash_attention_4"`

The example below demonstrates how to generate text with [Pipeline](/docs/transformers/main/en/main_classes/pipelines#transformers.Pipeline) or the [AutoModelForCausalLM](/docs/transformers/main/en/model_doc/auto#transformers.AutoModelForCausalLM) class.

```python
from transformers import pipeline

pipe = pipeline(
    task="text-generation",
    model="ibm-granite/granite-swash-3b-a600m",
)
pipe("Explain quantum computing in simple terms", max_new_tokens=50)
```

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-swash-3b-a600m")
model = AutoModelForCausalLM.from_pretrained(
    "ibm-granite/granite-swash-3b-a600m",
    device_map="auto",
    # eager default, also supports "flex_attention", "flash_attention_3", "flash_attention_4"
    attn_implementation="eager",
)

inputs = tokenizer("Explain quantum computing in simple terms", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## GraniteMoeSWAConfig[[transformers.GraniteMoeSWAConfig]]

#### transformers.GraniteMoeSWAConfig[[transformers.GraniteMoeSWAConfig]]

```python
transformers.GraniteMoeSWAConfig(transformers_version: str | None = None, architectures: list[str] | None = None, output_hidden_states: bool | None = False, return_dict: bool | None = True, dtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = None, chunk_size_feed_forward: int = 0, is_encoder_decoder: bool = False, id2label: dict[int, str] | dict[str, str] | None = None, label2id: dict[str, int] | dict[str, str] | None = None, problem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = None, vocab_size: int = 32000, hidden_size: int = 4096, intermediate_size: int = 11008, num_hidden_layers: int = 32, num_attention_heads: int = 32, num_key_value_heads: int | None = None, hidden_act: str = 'silu', max_position_embeddings: int = 2048, initializer_range: float = 0.02, rms_norm_eps: float = 1e-06, use_cache: bool = True, pad_token_id: int | None = None, bos_token_id: int | None = 1, eos_token_id: int | list[int] | None = 2, tie_word_embeddings: bool = False, rope_parameters: transformers.modeling_rope_utils.RopeParameters | dict | None = None, attention_bias: bool = False, attention_dropout: float | int | None = 0.0, embedding_multiplier: float | int | None = 1.0, logits_scaling: float | int | None = 1.0, residual_multiplier: float | int | None = 1.0, attention_multiplier: float | int | None = 1.0, num_local_experts: int | None = 8, num_experts_per_tok: int | None = 2, output_router_logits: bool | None = False, router_aux_loss_coef: float | None = 0.001, shared_intermediate_size: int = 0, sliding_window: int | None = 128, layer_types: list[str] | None = None, layer_rope_theta: list[float | int] | None = None)
```

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/granitemoe_swa/configuration_granitemoe_swa.py#L29)

**Parameters:**

vocab_size (`int`, *optional*, defaults to `32000`) : 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 `11008`) : Dimension of the MLP representations.

num_hidden_layers (`int`, *optional*, defaults to `32`) : Number of hidden layers in the Transformer decoder.

num_attention_heads (`int`, *optional*, defaults to `32`) : Number of attention heads for each attention layer in the Transformer decoder.

num_key_value_heads (`int`, *optional*) : This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`.

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 `2048`) : 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.

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

bos_token_id (`int`, *optional*, defaults to `1`) : Token id used for beginning-of-stream in the vocabulary.

eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `2`) : Token id used for end-of-stream in the vocabulary.

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.

embedding_multiplier (`Union[float, int]`, *optional*, defaults to `1.0`) : Scaling factor applied to the word embeddings. Used to scale the embeddings relative to the hidden size.

logits_scaling (`Union[float, int]`, *optional*, defaults to `1.0`) : Scaling factor applied to the output logits before computing the probability distribution.

residual_multiplier (`Union[float, int]`, *optional*, defaults to `1.0`) : Scaling factor applied to the residual connections.

attention_multiplier (`Union[float, int]`, *optional*, defaults to `1.0`) : Scaling factor applied to the attention weights.

num_local_experts (`int`, *optional*, defaults to `8`) : Number of local experts on each device. `num_experts` should be divisible by `num_local_experts`.

num_experts_per_tok (`int`, *optional*, defaults to `2`) : Number of experts to route each token to. This is the top-k value for the token-choice routing.

output_router_logits (`bool`, *optional*, defaults to `False`) : 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`) : Auxiliary load balancing loss coefficient. Used to penalize uneven expert routing in MoE models.

shared_intermediate_size (`int`, *optional*, defaults to 0) : intermediate size for shared experts. Defaults to `0`, which disables the shared experts.

sliding_window (`int`, *optional*, defaults to 128) : Size of the sliding attention window used by layers whose `layer_types` entry is `"sliding_attention"`.

layer_types (`list[str]`, *optional*) : Per-layer attention type, each either `"full_attention"` or `"sliding_attention"`. When `None`, every fourth layer (`i % 4 == 0`) uses full attention and the rest use sliding window attention.

layer_rope_theta (`list[float]`, *optional*) : Per-layer RoPE base (`theta`) frequency. `0` sets NoPE (no positional embedding) for that layer. Overrides global `rope_parameters["rope_theta"]`, which is only used when this list is not provided or specified (`layer_rope_theta = None`).

This is the configuration class to store the configuration of a GraniteMoeSWAModel. It is used to instantiate a Granitemoe Swa
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 [ibm-granite/granite-swash-3b-a600m](https://huggingface.co/ibm-granite/granite-swash-3b-a600m)

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

```python
>>> from transformers import GraniteMoeSWAModel, GraniteMoeSWAConfig

>>> # Initializing a GraniteMoeSWA configuration
>>> configuration = GraniteMoeSWAConfig()

>>> # Initializing a model from the configuration
>>> model = GraniteMoeSWAModel(configuration)

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

## GraniteMoeSWAModel[[transformers.GraniteMoeSWAModel]]

#### transformers.GraniteMoeSWAModel[[transformers.GraniteMoeSWAModel]]

```python
transformers.GraniteMoeSWAModel(config: GraniteMoeSWAConfig)
```

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/granitemoe_swa/modeling_granitemoe_swa.py#L497)

**Parameters:**

config ([GraniteMoeSWAConfig](/docs/transformers/main/en/model_doc/granitemoe_swa#transformers.GraniteMoeSWAConfig)) : 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/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

The bare Granitemoe Swa Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/main/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.

#### forward[[transformers.GraniteMoeSWAModel.forward]]

```python
forward(input_ids: typing.Optional[torch.LongTensor] = None, attention_mask: typing.Optional[torch.Tensor] = None, position_ids: typing.Optional[torch.LongTensor] = None, past_key_values: transformers.cache_utils.Cache | None = None, inputs_embeds: typing.Optional[torch.FloatTensor] = None, use_cache: bool | None = None, **kwargs: Unpack)
```

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/granitemoe_swa/modeling_granitemoe_swa.py#L523)

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

attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:  - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**.  [What are attention masks?](../glossary#attention-mask)

position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`.  [What are position IDs?](../glossary#position-ids)

past_key_values (`~cache_utils.Cache`, *optional*) : Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.  Only [Cache](/docs/transformers/main/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/main/en/internal/generation_utils#transformers.DynamicCache) will be initialized by default.  The model will output the same cache format that is fed as input.  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids` of shape `(batch_size, sequence_length)`.

inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) : Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix.

use_cache (`bool`, *optional*) : If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).

**Returns:** `MoeModelOutputWithPast` or `tuple(torch.FloatTensor)`

A `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 ([GraniteMoeSWAConfig](/docs/transformers/main/en/model_doc/granitemoe_swa#transformers.GraniteMoeSWAConfig)) and inputs.

The [GraniteMoeSWAModel](/docs/transformers/main/en/model_doc/granitemoe_swa#transformers.GraniteMoeSWAModel) 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.
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/main/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
  `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values`
  input) to speed up sequential decoding.
- **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
- **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
  heads.
- **router_logits** (`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 logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary
  loss for Mixture of Experts models.

## GraniteMoeSWAForCausalLM[[transformers.GraniteMoeSWAForCausalLM]]

#### transformers.GraniteMoeSWAForCausalLM[[transformers.GraniteMoeSWAForCausalLM]]

```python
transformers.GraniteMoeSWAForCausalLM(config: GraniteMoeSWAConfig)
```

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/granitemoe_swa/modeling_granitemoe_swa.py#L678)

**Parameters:**

config ([GraniteMoeSWAConfig](/docs/transformers/main/en/model_doc/granitemoe_swa#transformers.GraniteMoeSWAConfig)) : 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/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

The Granitemoe Swa Model for causal language modeling.

This model inherits from [PreTrainedModel](/docs/transformers/main/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.

#### forward[[transformers.GraniteMoeSWAForCausalLM.forward]]

```python
forward(input_ids: typing.Optional[torch.LongTensor] = None, attention_mask: typing.Optional[torch.Tensor] = None, position_ids: typing.Optional[torch.LongTensor] = None, past_key_values: transformers.cache_utils.Cache | None = None, inputs_embeds: typing.Optional[torch.FloatTensor] = None, labels: typing.Optional[torch.LongTensor] = None, output_router_logits: bool | None = None, logits_to_keep: typing.Union[int, torch.Tensor] = 0, **kwargs)
```

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/granitemoe_swa/modeling_granitemoe_swa.py#L697)

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

attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:  - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**.  [What are attention masks?](../glossary#attention-mask)

position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`.  [What are position IDs?](../glossary#position-ids)

past_key_values (`~cache_utils.Cache`, *optional*) : Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.  Only [Cache](/docs/transformers/main/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/main/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.

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*) : 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.

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:** `MoeCausalLMOutputWithPast` or `tuple(torch.FloatTensor)`

A `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 (`None`) and inputs.

The [GraniteMoeSWAForCausalLM](/docs/transformers/main/en/model_doc/granitemoe_swa#transformers.GraniteMoeSWAForCausalLM) 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).
- **aux_loss** (`torch.FloatTensor`, *optional*, returned when `labels` is provided) -- aux_loss for the sparse modules.
- **router_logits** (`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 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 when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/main/en/internal/generation_utils#transformers.Cache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
  `past_key_values` input) to speed up sequential decoding.
- **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
- **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
  heads.

Example:

```python
>>> from transformers import AutoTokenizer, GraniteMoeSWAForCausalLM

>>> model = GraniteMoeSWAForCausalLM.from_pretrained("ibm/PowerMoE-3b")
>>> tokenizer = AutoTokenizer.from_pretrained("ibm/PowerMoE-3b")

>>> 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."
```