# Mistral[[mistral]]

## 개요[[overview]]

미스트랄은 Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed가 작성한 [이 블로그 포스트](https://mistral.ai/news/announcing-mistral-7b/)에서 소개되었습니다.

블로그 포스트의 서두는 다음과 같습니다:

*미스트랄 AI팀은 현존하는 언어 모델 중 크기 대비 가장 강력한 미스트랄7B를 출시하게 되어 자랑스럽습니다.*

미스트랄-7B는 [mistral.ai](https://mistral.ai/)에서 출시한 첫 번째 대규모 언어 모델(LLM)입니다.

### 아키텍처 세부사항[[architectural-details]]

미스트랄-7B는 다음과 같은 구조적 특징을 가진 디코더 전용 트랜스포머입니다:

- 슬라이딩 윈도우 어텐션: 8k 컨텍스트 길이와 고정 캐시 크기로 훈련되었으며, 이론상 128K 토큰의 어텐션 범위를 가집니다.
- GQA(Grouped Query Attention): 더 빠른 추론이 가능하고 더 작은 크기의 캐시를 사용합니다.
- 바이트 폴백(Byte-fallback) BPE 토크나이저: 문자들이 절대 어휘 목록 외의 토큰으로 매핑되지 않도록 보장합니다.

더 자세한 내용은 [출시 블로그 포스트](https://mistral.ai/news/announcing-mistral-7b/)를 참조하세요.

### 라이선스[[license]]

`미스트랄-7B`는 아파치 2.0 라이선스로 출시되었습니다.

## 사용 팁[[usage-tips]]

미스트랄 AI팀은 다음 3가지 체크포인트를 공개했습니다:

- 기본 모델인 [미스트랄-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)은 인터넷 규모의 데이터에서 다음 토큰을 예측하도록 사전 훈련되었습니다.
- 지시 조정 모델인 [미스트랄-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)은 지도 미세 조정(SFT)과 직접 선호도 최적화(DPO)를 사용한 채팅에 최적화된 기본 모델입니다.
- 개선된 지시 조정 모델인 [미스트랄-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)는 v1을 개선한 버전입니다.

기본 모델은 다음과 같이 사용할 수 있습니다:

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

>>> model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", device_map="auto")
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")

>>> prompt = "My favourite condiment is"

>>> model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
>>> model.to(device)

>>> generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
>>> tokenizer.batch_decode(generated_ids)[0]
"My favourite condiment is to ..."
```

지시 조정 모델은 다음과 같이 사용할 수 있습니다:

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

>>> model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", device_map="auto")
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")

>>> messages = [
...     {"role": "user", "content": "What is your favourite condiment?"},
...     {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
...     {"role": "user", "content": "Do you have mayonnaise recipes?"}
... ]

>>> model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)

>>> generated_ids = model.generate(model_inputs, max_new_tokens=100, do_sample=True)
>>> tokenizer.batch_decode(generated_ids)[0]
"Mayonnaise can be made as follows: (...)"
```

지시 조정 모델은 입력이 올바른 형식으로 준비되도록 [채팅 템플릿](../chat_templating)을 적용해야 합니다.

## 플래시 어텐션을 이용한 미스트랄 속도향상[[speeding-up-mistral-by-using-flash-attention]]

위의 코드 스니펫들은 어떤 최적화 기법도 사용하지 않은 추론 과정을 보여줍니다. 하지만 모델 내부에서 사용되는 어텐션 메커니즘의 더 빠른 구현인 [플래시 어텐션2](../perf_train_gpu_one#flash-attention-2)을 활용하면 모델의 속도를 크게 높일 수 있습니다.

먼저, 슬라이딩 윈도우 어텐션 기능을 포함하는 플래시 어텐션2의 최신 버전을 설치해야 합니다.

```bash
pip install -U flash-attn --no-build-isolation
```

하드웨어와 플래시 어텐션2의 호환여부를 확인하세요. 이에 대한 자세한 내용은 [플래시 어텐션 저장소](https://github.com/Dao-AILab/flash-attention)의 공식 문서에서 확인할 수 있습니다. 또한 모델을 반정밀도(예: `torch.float16`)로 불러와야합니다.

플래시 어텐션2를 사용하여 모델을 불러오고 실행하려면 아래 코드 스니펫을 참조하세요:

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

>>> model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", dtype=torch.float16, attn_implementation="flash_attention_2", device_map="auto")
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")

>>> prompt = "My favourite condiment is"

>>> model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
>>> model.to(device)

>>> generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
>>> tokenizer.batch_decode(generated_ids)[0]
"My favourite condiment is to (...)"
```

### 기대하는 속도 향상[[expected-speedups]]

다음은 `mistralai/Mistral-7B-v0.1` 체크포인트를 사용한 트랜스포머의 기본 구현과 플래시 어텐션2 버전 모델 사이의 순수 추론 시간을 비교한 예상 속도 향상 다이어그램입니다.

### 슬라이딩 윈도우 어텐션[[sliding-window-attention]]

현재 구현은 슬라이딩 윈도우 어텐션 메커니즘과 메모리 효율적인 캐시 관리 기능을 지원합니다. 슬라이딩 윈도우 어텐션을 활성화하려면, 슬라이딩 윈도우 어텐션과 호환되는`flash-attn`(`>=2.3.0`)버전을 사용하면 됩니다. 

또한 플래시 어텐션2 모델은 더 메모리 효율적인 캐시 슬라이싱 메커니즘을 사용합니다. 미스트랄 모델의 공식 구현에서 권장하는 롤링 캐시 메커니즘을 따라, 캐시 크기를 고정(`self.config.sliding_window`)으로 유지하고, `padding_side="left"`인 경우에만 배치 생성(batch generation)을 지원하며, 현재 토큰의 절대 위치를 사용해 위치 임베딩을 계산합니다.

## 양자화로 미스트랄 크기 줄이기[[shrinking-down-mistral-using-quantization]]

미스트랄 모델은 70억 개의 파라미터를 가지고 있어, 절반의 정밀도(float16)로 약 14GB의 GPU RAM이 필요합니다. 각 파라미터가 2바이트로 저장되기 때문입니다. 하지만 [양자화](../quantization)를 사용하면 모델 크기를 줄일 수 있습니다. 모델을 4비트(즉, 파라미터당 반 바이트)로 양자화하면 약 3.5GB의 RAM만 필요합니다.

모델을 양자화하는 것은 `quantization_config`를 모델에 전달하는 것만큼 간단합니다. 아래에서는 BitsAndBytes 양자화를 사용하지만, 다른 양자화 방법은 [이 페이지](../quantization)를 참고하세요:

```python
>>> import torch
>>> from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

>>> # specify how to quantize the model
>>> quantization_config = BitsAndBytesConfig(
...         load_in_4bit=True,
...         bnb_4bit_quant_type="nf4",
...         bnb_4bit_compute_dtype="torch.float16",
... )

>>> model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", quantization_config=True, device_map="auto")
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")

>>> prompt = "My favourite condiment is"

>>> messages = [
...     {"role": "user", "content": "What is your favourite condiment?"},
...     {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
...     {"role": "user", "content": "Do you have mayonnaise recipes?"}
... ]

>>> model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)

>>> generated_ids = model.generate(model_inputs, max_new_tokens=100, do_sample=True)
>>> tokenizer.batch_decode(generated_ids)[0]
"The expected output"
```

이 모델은 [Younes Belkada](https://huggingface.co/ybelkada)와 [Arthur Zucker](https://huggingface.co/ArthurZ)가 기여했습니다.
원본 코드는 [이곳](https://github.com/mistralai/mistral-src)에서 확인할 수 있습니다.

## 리소스[[resources]]

미스트랄을 시작하는 데 도움이 되는 Hugging Face와 community 자료 목록(🌎로 표시됨) 입니다. 여기에 포함될 자료를 제출하고 싶으시다면 PR(Pull Request)를 열어주세요. 리뷰해 드리겠습니다! 자료는 기존 자료를 복제하는 대신 새로운 내용을 담고 있어야 합니다.

- 미스트랄-7B의 지도형 미세조정(SFT)을 수행하는 데모 노트북은 [이곳](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/Mistral/Supervised_fine_tuning_(SFT)_of_an_LLM_using_Hugging_Face_tooling.ipynb)에서 확인할 수 있습니다. 🌎
- 2024년에 Hugging Face 도구를 사용해 LLM을 미세 조정하는 방법에 대한 [블로그 포스트](https://www.philschmid.de/fine-tune-llms-in-2024-with-trl). 🌎
- Hugging Face의 [정렬(Alignment) 핸드북](https://github.com/huggingface/alignment-handbook)에는 미스트랄-7B를 사용한 지도형 미세 조정(SFT) 및 직접 선호 최적화(DPO)를 수행하기 위한 스크립트와 레시피가 포함되어 있습니다. 여기에는 단일 GPU에서 QLoRa 및 다중 GPU를 사용한 전체 미세 조정을 위한 스크립트가 포함되어 있습니다.
- [인과적 언어 모델링 작업 가이드](../tasks/language_modeling)

## MistralConfig[[transformers.MistralConfig]][[transformers.MistralConfig]]

#### transformers.MistralConfig[[transformers.MistralConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/mistral/configuration_mistral.py#L28)

This is the configuration class to store the configuration of a MistralModel. It is used to instantiate a Mistral
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 [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.6.2/ko/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.6.2/ko/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:

```python
>>> from transformers import MistralModel, MistralConfig

>>> # Initializing a Mistral 7B style configuration
>>> configuration = MistralConfig()

>>> # Initializing a model from the Mistral 7B style configuration
>>> model = MistralModel(configuration)

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

**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 `14336`) : 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*, defaults to `8`) : 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`.

head_dim (`int`, *optional*) : The attention head dimension. If None, it will default to hidden_size // 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 `131072`) : 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`.

sliding_window (`int`, *optional*, defaults to `4096`) : Sliding window attention window size. If `None`, no sliding window is applied.

attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities.

## MistralModel[[transformers.MistralModel]][[transformers.MistralModel]]

#### transformers.MistralModel[[transformers.MistralModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/mistral/modeling_mistral.py#L328)

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

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/ko/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.MistralModel.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/mistral/modeling_mistral.py#L345[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.6.2/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/ko/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/v5.6.2/ko/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.6.2/ko/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`).0[BaseModelOutputWithPast](/docs/transformers/v5.6.2/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPast](/docs/transformers/v5.6.2/ko/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 ([MistralConfig](/docs/transformers/v5.6.2/ko/model_doc/mistral#transformers.MistralConfig)) and inputs.
The [MistralModel](/docs/transformers/v5.6.2/ko/model_doc/mistral#transformers.MistralModel) 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/v5.6.2/ko/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.

**Parameters:**

config ([MistralConfig](/docs/transformers/v5.6.2/ko/model_doc/mistral#transformers.MistralConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.6.2/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[BaseModelOutputWithPast](/docs/transformers/v5.6.2/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or `tuple(torch.FloatTensor)``

A [BaseModelOutputWithPast](/docs/transformers/v5.6.2/ko/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 ([MistralConfig](/docs/transformers/v5.6.2/ko/model_doc/mistral#transformers.MistralConfig)) and inputs.

## MistralForCausalLM[[transformers.MistralForCausalLM]][[transformers.MistralForCausalLM]]

#### transformers.MistralForCausalLM[[transformers.MistralForCausalLM]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/mistral/modeling_mistral.py#L402)

The Mistral Model for causal language modeling.

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/ko/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.MistralForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/mistral/modeling_mistral.py#L416[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | 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": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.6.2/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/ko/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/v5.6.2/ko/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.6.2/ko/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]`.
- **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[CausalLMOutputWithPast](/docs/transformers/v5.6.2/ko/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithPast](/docs/transformers/v5.6.2/ko/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 ([MistralConfig](/docs/transformers/v5.6.2/ko/model_doc/mistral#transformers.MistralConfig)) and inputs.
The [MistralForCausalLM](/docs/transformers/v5.6.2/ko/model_doc/mistral#transformers.MistralForCausalLM) 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](/docs/transformers/v5.6.2/ko/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, MistralForCausalLM

>>> model = MistralForCausalLM.from_pretrained("meta-mistral/Mistral-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-mistral/Mistral-2-7b-hf")

>>> 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."
```

**Parameters:**

config ([MistralForCausalLM](/docs/transformers/v5.6.2/ko/model_doc/mistral#transformers.MistralForCausalLM)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.6.2/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[CausalLMOutputWithPast](/docs/transformers/v5.6.2/ko/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)``

A [CausalLMOutputWithPast](/docs/transformers/v5.6.2/ko/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 ([MistralConfig](/docs/transformers/v5.6.2/ko/model_doc/mistral#transformers.MistralConfig)) and inputs.

## MistralForSequenceClassification[[transformers.MistralForSequenceClassification]][[transformers.MistralForSequenceClassification]]

#### transformers.MistralForSequenceClassification[[transformers.MistralForSequenceClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/mistral/modeling_mistral.py#L479)

forwardtransformers.MistralForSequenceClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/modeling_layers.py#L110[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | 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": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.6.2/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/ko/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/v5.6.2/ko/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.6.2/ko/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]`.
- **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`SequenceClassifierOutputWithPast` or `tuple(torch.FloatTensor)`A `SequenceClassifierOutputWithPast` or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration (`None`) and inputs.
The `GenericForSequenceClassification` forward method, overrides the `__call__` special method.

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

- **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).
- **past_key_values** (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [Cache](/docs/transformers/v5.6.2/ko/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.

**Parameters:**

input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.6.2/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/ko/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/v5.6.2/ko/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.6.2/ko/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]`.

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:**

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

A `SequenceClassifierOutputWithPast` or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration (`None`) and inputs.

## MistralForTokenClassification[[transformers.MistralForTokenClassification]][[transformers.MistralForTokenClassification]]

#### transformers.MistralForTokenClassification[[transformers.MistralForTokenClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/mistral/modeling_mistral.py#L475)

forwardtransformers.MistralForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/modeling_layers.py#L253[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | 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": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.6.2/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/ko/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/v5.6.2/ko/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.6.2/ko/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]`.
- **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[TokenClassifierOutput](/docs/transformers/v5.6.2/ko/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`A [TokenClassifierOutput](/docs/transformers/v5.6.2/ko/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration (`None`) and inputs.
The `GenericForTokenClassification` forward method, overrides the `__call__` special method.

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

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Classification loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.num_labels)`) -- Classification 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.

**Parameters:**

input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.6.2/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/ko/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/v5.6.2/ko/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache). If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.6.2/ko/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]`.

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:**

`[TokenClassifierOutput](/docs/transformers/v5.6.2/ko/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)``

A [TokenClassifierOutput](/docs/transformers/v5.6.2/ko/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration (`None`) and inputs.