transformers/main/ja/model_doc/ctrl.md

# CTRL

## Overview

CTRL モデルは、Nitish Shirish Keskar*、Bryan McCann*、Lav R. Varshney、Caiming Xiong, Richard Socher によって [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://huggingface.co/papers/1909.05858) で提案されました。
リチャード・ソーチャー。これは、非常に大規模なコーパスの言語モデリングを使用して事前トレーニングされた因果的 (一方向) トランスフォーマーです
最初のトークンが制御コード (リンク、書籍、Wikipedia など) として予約されている、約 140 GB のテキスト データ。

論文の要約は次のとおりです。

*大規模な言語モデルは有望なテキスト生成機能を示していますが、ユーザーは特定の言語モデルを簡単に制御できません
生成されたテキストの側面。 16 億 3,000 万パラメータの条件付きトランスフォーマー言語モデルである CTRL をリリースします。
スタイル、コンテンツ、タスク固有の動作を制御する制御コードを条件付けるように訓練されています。制御コードは
生のテキストと自然に共生する構造から派生し、教師なし学習の利点を維持しながら、
テキスト生成をより明示的に制御できるようになります。これらのコードを使用すると、CTRL でどの部分が予測されるのかを予測することもできます。
トレーニング データにはシーケンスが与えられる可能性が最も高くなります。これにより、大量のデータを分析するための潜在的な方法が提供されます。
モデルベースのソース帰属を介して。*

このモデルは、[keskarnitishr](https://huggingface.co/keskarnitishr) によって提供されました。元のコードが見つかる
[こちら](https://github.com/salesforce/Salesforce/ctrl)。

## Usage tips

- CTRL は制御コードを利用してテキストを生成します。生成を特定の単語や文で開始する必要があります。
  またはリンクして一貫したテキストを生成します。 [元の実装](https://github.com/salesforce/Salesforce/ctrl) を参照してください。
  詳しくは。
- CTRL は絶対位置埋め込みを備えたモデルであるため、通常は入力を右側にパディングすることをお勧めします。
  左。
- CTRL は因果言語モデリング (CLM) の目的でトレーニングされているため、次の予測に強力です。
  シーケンス内のトークン。この機能を利用すると、CTRL は構文的に一貫したテキストを生成できるようになります。
  *run_generation.py* サンプル スクリプトで確認できます。
- PyTorch モデルは、以前に計算されたキーと値のアテンション ペアである`past_key_values`を入力として受け取ることができます。
  TensorFlow モデルは`past`を入力として受け入れます。 `past_key_values`値を使用すると、モデルが再計算されなくなります。
  テキスト生成のコンテキストで事前に計算された値。 [`forward`](model_doc/ctrl#transformers.CTRLModel.forward) を参照してください。
  この引数の使用法の詳細については、メソッドを参照してください。

## Resources

- [テキスト分類タスクガイド(英語版)](../../en/tasks/sequence_classification)
- [因果言語モデリング タスク ガイド](../tasks/language_modeling)

## CTRLConfig[[transformers.CTRLConfig]]

#### transformers.CTRLConfig[[transformers.CTRLConfig]]

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

This is the configuration class to store the configuration of a CTRLModel. It is used to instantiate a Ctrl
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 [Salesforce/ctrl](https://huggingface.co/Salesforce/ctrl)

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

Examples:

```python
>>> from transformers import CTRLConfig, CTRLModel

>>> # Initializing a CTRL configuration
>>> configuration = CTRLConfig()

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

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

**Parameters:**

vocab_size (`int`, *optional*, defaults to `246534`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`.

n_positions (`int`, *optional*, defaults to `256`) : The maximum sequence length that this model might ever be used with.

n_embd (`int`, *optional*, defaults to `1280`) : Dimensionality of the embeddings and hidden states.

dff (`int`, *optional*, defaults to 8192) : Dimensionality of the inner dimension of the feed forward networks (FFN).

n_layer (`int`, *optional*, defaults to `48`) : Number of hidden layers in the Transformer decoder.

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

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

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

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

initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

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*) : Token id used for beginning-of-stream in the vocabulary.

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

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

## CTRLTokenizer[[transformers.CTRLTokenizer]]

#### transformers.CTRLTokenizer[[transformers.CTRLTokenizer]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/ctrl/tokenization_ctrl.py#L107)

Construct a CTRL tokenizer. Based on Byte-Pair-Encoding.

This tokenizer inherits from [PreTrainedTokenizer](/docs/transformers/main/ja/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.CTRLTokenizer.save_vocabularyhttps://github.com/huggingface/transformers/blob/main/src/transformers/tokenization_python.py#L1358[{"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, or empty tuple if no files saved.

Default implementation for common vocabulary saving patterns.
Saves self.encoder/self.vocab as JSON, optionally with self.bpe_ranks as merges.
Returns empty tuple if no vocabulary exists.

Override this method if your tokenizer needs custom saving logic (e.g., SentencePiece models,
multiple vocabulary files, or special file formats).

**Parameters:**

vocab_file (`str`) : Path to the vocabulary file.

merges_file (`str`) : Path to the merges file.

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.

**Returns:**

``tuple[str, ...]``

Paths to the files saved, or empty tuple if no files saved.

## CTRLModel[[transformers.CTRLModel]]

#### transformers.CTRLModel[[transformers.CTRLModel]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/ctrl/modeling_ctrl.py#L196)

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

This model inherits from [PreTrainedModel](/docs/transformers/main/ja/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.CTRLModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/ctrl/modeling_ctrl.py#L227[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **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/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

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

  Only `Cache` instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, `DynamicCache` will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **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)
- **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

  [What are token type IDs?](../glossary#token-type-ids)
- **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)
- **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`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/main/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[BaseModelOutputWithPast](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPast](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([CTRLConfig](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLConfig)) and inputs.
The [CTRLModel](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLModel) forward method, overrides the `__call__` special method.

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

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

  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
  hidden_size)` is output.
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `Cache` instance. For more details, see our [kv cache guide](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.

Example:

```python
>>> from transformers import AutoTokenizer, CTRLModel
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("Salesforce/ctrl")
>>> model = CTRLModel.from_pretrained("Salesforce/ctrl")

>>> # CTRL was trained with control codes as the first token
>>> inputs = tokenizer("Opinion My dog is cute", return_tensors="pt")
>>> assert inputs["input_ids"][0, 0].item() in tokenizer.control_codes.values()

>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 5, 1280]
```

**Parameters:**

config ([CTRLModel](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLModel)) : 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/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [BaseModelOutputWithPast](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([CTRLConfig](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLConfig)) and inputs.

## CTRLLMHeadModel[[transformers.CTRLLMHeadModel]]

#### transformers.CTRLLMHeadModel[[transformers.CTRLLMHeadModel]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/ctrl/modeling_ctrl.py#L375)

The CTRL Model transformer with a language modeling head on top (linear layer with weights tied to the input
embeddings).

This model inherits from [PreTrainedModel](/docs/transformers/main/ja/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.CTRLLMHeadModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/ctrl/modeling_ctrl.py#L386[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**kwargs", "val": ""}]- **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/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

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

  Only `Cache` instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, `DynamicCache` will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **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)
- **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

  [What are token type IDs?](../glossary#token-type-ids)
- **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)
- **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 language modeling. Note that the labels **are shifted** inside the model, i.e. you can set
  `labels = input_ids` Indices are selected in `[-100, 0, ..., config.vocab_size]` All labels set to `-100`
  are ignored (masked), the loss is only computed for labels in `[0, ..., config.vocab_size]`
- **use_cache** (`bool`, *optional*) --
  If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
  `past_key_values`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/main/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
- **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[CausalLMOutputWithPast](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithPast](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([CTRLConfig](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLConfig)) and inputs.
The [CTRLLMHeadModel](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLLMHeadModel) forward method, overrides the `__call__` special method.

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

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Language modeling loss (for next-token prediction).
- **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a `Cache` instance. For more details, see our [kv cache guide](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
>>> import torch
>>> from transformers import AutoTokenizer, CTRLLMHeadModel

>>> tokenizer = AutoTokenizer.from_pretrained("Salesforce/ctrl")
>>> model = CTRLLMHeadModel.from_pretrained("Salesforce/ctrl")

>>> # CTRL was trained with control codes as the first token
>>> inputs = tokenizer("Wikipedia The llama is", return_tensors="pt")
>>> assert inputs["input_ids"][0, 0].item() in tokenizer.control_codes.values()

>>> sequence_ids = model.generate(inputs["input_ids"])
>>> sequences = tokenizer.batch_decode(sequence_ids)
>>> sequences
['Wikipedia The llama is a member of the family Bovidae. It is native to the Andes of Peru,']

>>> outputs = model(**inputs, labels=inputs["input_ids"])
>>> round(outputs.loss.item(), 2)
9.21

>>> list(outputs.logits.shape)
[1, 5, 246534]
```

**Parameters:**

config ([CTRLLMHeadModel](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLLMHeadModel)) : 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/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [CausalLMOutputWithPast](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([CTRLConfig](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLConfig)) and inputs.

## CTRLForSequenceClassification[[transformers.CTRLForSequenceClassification]]

#### transformers.CTRLForSequenceClassification[[transformers.CTRLForSequenceClassification]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/ctrl/modeling_ctrl.py#L505)

The CTRL Model transformer with a sequence classification head on top (linear layer).
[CTRLForSequenceClassification](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLForSequenceClassification) uses the last token in order to do the classification, as other causal models
(e.g. GPT-2) do. Since it does classification on the last token, it requires to know the position of the last
token. If a `pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in
each row. If no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot
guess the padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last
value in each row of the batch).

This model inherits from [PreTrainedModel](/docs/transformers/main/ja/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.CTRLForSequenceClassification.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/ctrl/modeling_ctrl.py#L515[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **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/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

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

  Only `Cache` instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, `DynamicCache` will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **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)
- **token_type_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

  [What are token type IDs?](../glossary#token-type-ids)
- **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)
- **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,)`, *optional*) --
  Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
  config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
  `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
- **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`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/main/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[SequenceClassifierOutput](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`A [SequenceClassifierOutput](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) 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 ([CTRLConfig](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLConfig)) and inputs.
The [CTRLForSequenceClassification](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLForSequenceClassification) forward method, overrides the `__call__` special method.

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

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Classification (or regression if config.num_labels==1) loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`) -- Classification (or regression if config.num_labels==1) scores (before SoftMax).
- **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 of single-label classification:

```python
>>> import torch
>>> from transformers import AutoTokenizer, CTRLForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("Salesforce/ctrl")
>>> model = CTRLForSequenceClassification.from_pretrained("Salesforce/ctrl")

>>> # CTRL was trained with control codes as the first token
>>> inputs = tokenizer("Opinion My dog is cute", return_tensors="pt")
>>> assert inputs["input_ids"][0, 0].item() in tokenizer.control_codes.values()

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_id = logits.argmax().item()
>>> model.config.id2label[predicted_class_id]
'LABEL_0'
```

```python
>>> import torch

>>> torch.manual_seed(42)
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = CTRLForSequenceClassification.from_pretrained("Salesforce/ctrl", num_labels=num_labels)

>>> labels = torch.tensor(1)
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
0.93
```

Example of multi-label classification:

```python
>>> import torch
>>> from transformers import AutoTokenizer, CTRLForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("Salesforce/ctrl")
>>> model = CTRLForSequenceClassification.from_pretrained(
...     "Salesforce/ctrl", problem_type="multi_label_classification"
... )

>>> # CTRL was trained with control codes as the first token
>>> inputs = tokenizer("Opinion My dog is cute", return_tensors="pt")
>>> assert inputs["input_ids"][0, 0].item() in tokenizer.control_codes.values()

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predicted_class_id = logits.argmax().item()
>>> model.config.id2label[predicted_class_id]
'LABEL_0'
```

```python
>>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
>>> num_labels = len(model.config.id2label)
>>> model = CTRLForSequenceClassification.from_pretrained("Salesforce/ctrl", num_labels=num_labels)

>>> num_labels = len(model.config.id2label)
>>> labels = torch.nn.functional.one_hot(torch.tensor([predicted_class_id]), num_classes=num_labels).to(
...     torch.float
... )
>>> loss = model(**inputs, labels=labels).loss
>>> loss.backward()
```

**Parameters:**

config ([CTRLForSequenceClassification](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLForSequenceClassification)) : 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/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [SequenceClassifierOutput](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) 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 ([CTRLConfig](/docs/transformers/main/ja/model_doc/ctrl#transformers.CTRLConfig)) and inputs.