transformers/main/en/model_doc/bert-generation.md

# BertGeneration

[BertGeneration](https://huggingface.co/papers/1907.12461) leverages pretrained BERT checkpoints for sequence-to-sequence tasks with the [EncoderDecoderModel](/docs/transformers/main/en/model_doc/encoder-decoder#transformers.EncoderDecoderModel) architecture. BertGeneration adapts the `BERT` for generative tasks.

You can find all the original BERT checkpoints under the [BERT](https://huggingface.co/collections/google/bert-release-64ff5e7a4be99045d1896dbc) collection.

> [!TIP]
> This model was contributed by [patrickvonplaten](https://huggingface.co/patrickvonplaten).
>
> Click on the BertGeneration models in the right sidebar for more examples of how to apply BertGeneration to different sequence generation tasks.

The example below demonstrates how to use BertGeneration with [EncoderDecoderModel](/docs/transformers/main/en/model_doc/encoder-decoder#transformers.EncoderDecoderModel) for sequence-to-sequence tasks.

```python
from transformers import AutoTokenizer, EncoderDecoderModel

model = EncoderDecoderModel.from_pretrained("google/roberta2roberta_L-24_discofuse", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_discofuse")

input_ids = tokenizer(
    "Plants create energy through ", add_special_tokens=False, return_tensors="pt"
).input_ids

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 [BitsAndBytesConfig](../quantizationbitsandbytes) to quantize the weights to 4-bit.

```python
import torch

from transformers import AutoTokenizer, BitsAndBytesConfig, EncoderDecoderModel

# Configure 4-bit quantization
quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.float16
)

model = EncoderDecoderModel.from_pretrained(
    "google/roberta2roberta_L-24_discofuse",
    quantization_config=quantization_config,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_discofuse")

input_ids = tokenizer(
    "Plants create energy through ", add_special_tokens=False, return_tensors="pt"
).input_ids

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

## Notes

- [BertGenerationEncoder](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationEncoder) and [BertGenerationDecoder](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationDecoder) should be used in combination with [EncoderDecoderModel](/docs/transformers/main/en/model_doc/encoder-decoder#transformers.EncoderDecoderModel) for sequence-to-sequence tasks.

   ```python
   from transformers import BertGenerationEncoder, BertGenerationDecoder, BertTokenizer, EncoderDecoderModel
   
   # leverage checkpoints for Bert2Bert model
   # use BERT's cls token as BOS token and sep token as EOS token
   encoder = BertGenerationEncoder.from_pretrained("google-bert/bert-large-uncased", bos_token_id=101, eos_token_id=102)
   # add cross attention layers and use BERT's cls token as BOS token and sep token as EOS token
   decoder = BertGenerationDecoder.from_pretrained(
       "google-bert/bert-large-uncased", add_cross_attention=True, is_decoder=True, bos_token_id=101, eos_token_id=102
   )
   bert2bert = EncoderDecoderModel(encoder=encoder, decoder=decoder)

   # create tokenizer
   tokenizer = BertTokenizer.from_pretrained("google-bert/bert-large-uncased")

   input_ids = tokenizer(
       "This is a long article to summarize", add_special_tokens=False, return_tensors="pt"
   ).input_ids
   labels = tokenizer("This is a short summary", return_tensors="pt").to(model.device).input_ids

   # train
   loss = bert2bert(input_ids=input_ids, decoder_input_ids=labels, labels=labels).loss
   loss.backward()
   ```

- For summarization, sentence splitting, sentence fusion and translation, no special tokens are required for the input.
- No EOS token should be added to the end of the input for most generation tasks.

## BertGenerationConfig[[transformers.BertGenerationConfig]]

#### transformers.BertGenerationConfig[[transformers.BertGenerationConfig]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bert_generation/configuration_bert_generation.py#L24)

This is the configuration class to store the configuration of a Bert GenerationModel. It is used to instantiate a Bert Generation
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/bert_for_seq_generation_L-24_bbc_encoder](https://huggingface.co/google/bert_for_seq_generation_L-24_bbc_encoder)

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.

Examples:

```python
>>> from transformers import BertGenerationConfig, BertGenerationEncoder

>>> # Initializing a BertGeneration config
>>> configuration = BertGenerationConfig()

>>> # Initializing a model (with random weights) from the config
>>> model = BertGenerationEncoder(configuration)

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

**Parameters:**

vocab_size (`int`, *optional*, defaults to `50358`) : 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 `1024`) : Dimension of the hidden representations.

num_hidden_layers (`int`, *optional*, defaults to `24`) : Number of hidden layers in the Transformer decoder.

num_attention_heads (`int`, *optional*, defaults to `16`) : Number of attention heads for each attention layer in the Transformer decoder.

intermediate_size (`int`, *optional*, defaults to `4096`) : Dimension of the MLP representations.

hidden_act (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc.

hidden_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

attention_probs_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout ratio for the attention probabilities.

max_position_embeddings (`int`, *optional*, defaults to `512`) : 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.

layer_norm_eps (`float`, *optional*, defaults to `1e-12`) : The epsilon used by the layer normalization layers.

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

bos_token_id (`int`, *optional*, defaults to `2`) : Token id used for beginning-of-stream in the vocabulary.

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

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.

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.

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

## BertGenerationTokenizer[[transformers.BertGenerationTokenizer]]

#### transformers.BertGenerationTokenizer[[transformers.BertGenerationTokenizer]]

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

Construct a BertGeneration tokenizer. Based on [SentencePiece](https://github.com/google/sentencepiece).

This tokenizer inherits from [PreTrainedTokenizer](/docs/transformers/main/en/main_classes/tokenizer#transformers.PythonBackend) which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.

save_vocabularytransformers.BertGenerationTokenizer.save_vocabularyhttps://github.com/huggingface/transformers/blob/main/src/transformers/tokenization_utils_sentencepiece.py#L237[{"name": "save_directory", "val": ": str"}, {"name": "filename_prefix", "val": ": str | None = None"}]- **save_directory** (`str`) --
  The directory in which to save the vocabulary.
- **filename_prefix** (`str`, *optional*) --
  An optional prefix to add to the named of the saved files.0`tuple(str)`Paths to the files saved.

Save the sentencepiece vocabulary (copy original file) to a directory.

**Parameters:**

vocab_file (`str`) : [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that contains the vocabulary necessary to instantiate a tokenizer.

bos_token (`str`, *optional*, defaults to `"<s>"`) : The begin of sequence token.

eos_token (`str`, *optional*, defaults to `"</s>"`) : The end of sequence token.

unk_token (`str`, *optional*, defaults to `"<unk>"`) : The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.

pad_token (`str`, *optional*, defaults to `"<pad>"`) : The token used for padding, for example when batching sequences of different lengths.

sep_token (`str`, *optional*, defaults to `"< --:::>"`): The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens.

sp_model_kwargs (`dict`, *optional*) : Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things, to set:  - `enable_sampling`: Enable subword regularization. - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.  - `nbest_size = {0,1}`: No sampling is performed. - `nbest_size > 1`: samples from the nbest_size results. - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm.  - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout.

**Returns:**

``tuple(str)``

Paths to the files saved.

## BertGenerationEncoder[[transformers.BertGenerationEncoder]]

#### transformers.BertGenerationEncoder[[transformers.BertGenerationEncoder]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bert_generation/modeling_bert_generation.py#L460)

The bare BertGeneration model transformer 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.

forwardtransformers.BertGenerationEncoder.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/bert_generation/modeling_bert_generation.py#L494[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "encoder_hidden_states", "val": ": torch.Tensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.Tensor` 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.Tensor` 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)
- **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.
- **encoder_hidden_states** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
  if the model is configured as a decoder.
- **encoder_attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
  the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **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)`.
- **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[BaseModelOutputWithPastAndCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPastAndCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions) 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 ([BertGenerationConfig](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationConfig)) and inputs.
The [BertGenerationEncoder](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationEncoder) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module`
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.

- **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model.

  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
  hidden_size)` is output.
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/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.
- **cross_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` and `config.add_cross_attention=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.

**Parameters:**

config ([BertGenerationEncoder](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationEncoder)) : 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.

**Returns:**

`[BaseModelOutputWithPastAndCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions) or `tuple(torch.FloatTensor)``

A [BaseModelOutputWithPastAndCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions) 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 ([BertGenerationConfig](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationConfig)) and inputs.

## BertGenerationDecoder[[transformers.BertGenerationDecoder]]

#### transformers.BertGenerationDecoder[[transformers.BertGenerationDecoder]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bert_generation/modeling_bert_generation.py#L608)

BertGeneration Model with a `language modeling` head on top for CLM fine-tuning.

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.

forwardtransformers.BertGenerationDecoder.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/bert_generation/modeling_bert_generation.py#L633[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "encoder_hidden_states", "val": ": torch.Tensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "past_key_values", "val": ": tuple[tuple[torch.FloatTensor]] | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.Tensor` 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.Tensor` 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)
- **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.
- **encoder_hidden_states** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
  if the model is configured as a decoder.
- **encoder_attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
  the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
  `[-100, 0, ..., config.vocab_size]` (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]`
- **past_key_values** (`tuple[tuple[torch.FloatTensor]]`, *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)`.
- **use_cache** (`bool`, *optional*) --
  If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
  `past_key_values`).
- **logits_to_keep** (`Union[int, torch.Tensor]`, *optional*, defaults to `0`) --
  If an `int`, compute logits for the last `logits_to_keep` tokens. If `0`, calculate logits for all
  `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that
  token can save memory, which becomes pretty significant for long sequences or large vocabulary size.
  If a `torch.Tensor`, must be 1D corresponding to the indices to keep in the sequence length dimension.
  This is useful when using packed tensor format (single dimension for batch and sequence length).0[CausalLMOutputWithCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) 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 ([BertGenerationConfig](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationConfig)) and inputs.
The [BertGenerationDecoder](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationDecoder) 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).
- **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.
- **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)`.

  Cross attentions weights after the attention softmax, used to compute the weighted average in the
  cross-attention heads.
- **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 attention blocks) that can be used (see
  `past_key_values` input) to speed up sequential decoding.

Example:

```python
>>> from transformers import AutoTokenizer, BertGenerationDecoder, BertGenerationConfig
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google/bert_for_seq_generation_L-24_bbc_encoder")
>>> config = BertGenerationConfig.from_pretrained("google/bert_for_seq_generation_L-24_bbc_encoder")
>>> config.is_decoder = True
>>> model = BertGenerationDecoder.from_pretrained(
...     "google/bert_for_seq_generation_L-24_bbc_encoder", config=config
... )

>>> inputs = tokenizer("Hello, my dog is cute", return_token_type_ids=False, return_tensors="pt")
>>> outputs = model(**inputs)

>>> prediction_logits = outputs.logits
```

**Parameters:**

config ([BertGenerationDecoder](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationDecoder)) : 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.

**Returns:**

`[CausalLMOutputWithCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)``

A [CausalLMOutputWithCrossAttentions](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) 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 ([BertGenerationConfig](/docs/transformers/main/en/model_doc/bert-generation#transformers.BertGenerationConfig)) and inputs.