# XLM-RoBERTa

[XLM-RoBERTa](https://huggingface.co/papers/1911.02116) is a large multilingual masked language model trained on 2.5TB of filtered CommonCrawl data across 100 languages. It shows that scaling the model provides strong performance gains on high-resource and low-resource languages. The model uses the [RoBERTa](./roberta) pretraining objectives on the [XLM](./xlm) model.

You can find all the original XLM-RoBERTa checkpoints under the [Facebook AI community](https://huggingface.co/FacebookAI) organization.

> [!TIP]
> Click on the XLM-RoBERTa models in the right sidebar for more examples of how to apply XLM-RoBERTa to different cross-lingual tasks like classification, translation, and question answering.

The example below demonstrates how to predict the `` token with [Pipeline](/docs/transformers/v5.6.2/en/main_classes/pipelines#transformers.Pipeline), [AutoModel](/docs/transformers/v5.6.2/en/model_doc/auto#transformers.AutoModel), and from the command line.

```python
import torch
from transformers import pipeline

pipeline = pipeline(
    task="fill-mask",
    model="FacebookAI/xlm-roberta-base",
    dtype=torch.float16,
    device=0
)
# Example in French
pipeline("Bonjour, je suis un modèle .")
```

```python
from transformers import AutoModelForMaskedLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained(
    "FacebookAI/xlm-roberta-base"
)
model = AutoModelForMaskedLM.from_pretrained(
    "FacebookAI/xlm-roberta-base",
    dtype=torch.float16,
    device_map="auto",
    attn_implementation="sdpa"
)

# Prepare input
inputs = tokenizer("Bonjour, je suis un modèle .", return_tensors="pt").to(model.device)

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

masked_index = torch.where(inputs['input_ids'] == tokenizer.mask_token_id)[1]
predicted_token_id = predictions[0, masked_index].argmax(dim=-1)
predicted_token = tokenizer.decode(predicted_token_id)

print(f"The predicted token is: {predicted_token}")
```

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

The example below uses [bitsandbytes](../quantization/bitsandbytes) the quantive the weights to 4 bits

```python
import torch
from transformers import AutoModelForMaskedLM, AutoTokenizer, BitsAndBytesConfig

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16
    bnb_4bit_quant_type="nf4",  # or "fp4" for float 4-bit quantization
    bnb_4bit_use_double_quant=True,  # use double quantization for better performance
)
tokenizer = AutoTokenizer.from_pretrained("facebook/xlm-roberta-large")
model = AutoModelForMaskedLM.from_pretrained(
    "facebook/xlm-roberta-large",
    dtype=torch.float16,
    device_map="auto",
    attn_implementation="flash_attention_2",
    quantization_config=quantization_config
)

inputs = tokenizer("Bonjour, je suis un modèle .", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Notes

- Unlike some XLM models, XLM-RoBERTa doesn't require `lang` tensors to understand what language is being used. It automatically determines the language from the input IDs

## Resources

A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with XLM-RoBERTa. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

- A blog post on how to [finetune XLM RoBERTa for multiclass classification with Habana Gaudi on AWS](https://www.philschmid.de/habana-distributed-training)
- [XLMRobertaForSequenceClassification](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForSequenceClassification) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/text-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/text_classification.ipynb)..
- [Text classification](https://huggingface.co/docs/transformers/tasks/sequence_classification) chapter of the 🤗 Hugging Face Task Guides.
- [Text classification task guide](../tasks/sequence_classification)

- [XLMRobertaForTokenClassification](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForTokenClassification) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/token-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/token_classification.ipynb).
- [Token classification](https://huggingface.co/course/chapter7/2?fw=pt) chapter of the 🤗 Hugging Face Course.
- [Token classification task guide](../tasks/token_classification)

- [XLMRobertaForCausalLM](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForCausalLM) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/language-modeling) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling.ipynb).
- [Causal language modeling](https://huggingface.co/docs/transformers/tasks/language_modeling) chapter of the 🤗 Hugging Face Task Guides.
- [Causal language modeling task guide](../tasks/language_modeling)

- [XLMRobertaForMaskedLM](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForMaskedLM) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/language-modeling#robertabertdistilbert-and-masked-language-modeling) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling.ipynb).
- [Masked language modeling](https://huggingface.co/course/chapter7/3?fw=pt) chapter of the 🤗 Hugging Face Course.
- [Masked language modeling](../tasks/masked_language_modeling)

- [XLMRobertaForQuestionAnswering](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForQuestionAnswering) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/question-answering) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/question_answering.ipynb).
- [Question answering](https://huggingface.co/course/chapter7/7?fw=pt) chapter of the 🤗 Hugging Face Course.
- [Question answering task guide](../tasks/question_answering)

**Multiple choice**

- [XLMRobertaForMultipleChoice](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForMultipleChoice) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/multiple-choice) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/multiple_choice.ipynb).
- [Multiple choice task guide](../tasks/multiple_choice)

🚀 Deploy

- A blog post on how to [Deploy Serverless XLM RoBERTa on AWS Lambda](https://www.philschmid.de/multilingual-serverless-xlm-roberta-with-huggingface).

This implementation is the same as RoBERTa. Refer to the [documentation of RoBERTa](roberta) for usage examples as well as the information relative to the inputs and outputs.

## XLMRobertaConfig[[transformers.XLMRobertaConfig]]

#### transformers.XLMRobertaConfig[[transformers.XLMRobertaConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/configuration_xlm_roberta.py#L25)

This is the configuration class to store the configuration of a Xlm RobertaModel. It is used to instantiate a Xlm Roberta
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 [FacebookAI/xlm-mlm-en-2048](https://huggingface.co/FacebookAI/xlm-mlm-en-2048)

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

Examples:

```python
>>> from transformers import XLMRobertaConfig, XLMRobertaModel

>>> # Initializing a XLM-RoBERTa FacebookAI/xlm-roberta-base style configuration
>>> configuration = XLMRobertaConfig()

>>> # Initializing a model (with random weights) from the FacebookAI/xlm-roberta-base style configuration
>>> model = XLMRobertaModel(configuration)

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

**Parameters:**

vocab_size (`int`, *optional*, defaults to `30522`) : 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 `768`) : Dimension of the hidden representations.

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

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

intermediate_size (`int`, *optional*, defaults to `3072`) : 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.

type_vocab_size (`int`, *optional*, defaults to `2`) : The vocabulary size of the `token_type_ids`.

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 `1`) : Token id used for padding in the vocabulary.

bos_token_id (`int`, *optional*, defaults to `0`) : 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.

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.

classifier_dropout (`Union[float, int]`, *optional*) : The dropout ratio for classifier.

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.

## XLMRobertaTokenizer[[transformers.XLMRobertaTokenizer]]

#### transformers.XLMRobertaTokenizer[[transformers.XLMRobertaTokenizer]]

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

Construct an XLM-RoBERTa tokenizer (backed by HuggingFace's tokenizers library). Based on SentencePiece.

This tokenizer inherits from [TokenizersBackend](/docs/transformers/v5.6.2/en/main_classes/tokenizer#transformers.TokenizersBackend) which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.

get_special_tokens_masktransformers.XLMRobertaTokenizer.get_special_tokens_maskhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/tokenization_utils_base.py#L1315[{"name": "token_ids_0", "val": ": list[int]"}, {"name": "token_ids_1", "val": ": list[int] | None = None"}, {"name": "already_has_special_tokens", "val": ": bool = False"}]- **token_ids_0** -- List of IDs for the (possibly already formatted) sequence.
- **token_ids_1** -- Unused when `already_has_special_tokens=True`. Must be None in that case.
- **already_has_special_tokens** -- Whether the sequence is already formatted with special tokens.0A list of integers in the range [0, 1]1 for a special token, 0 for a sequence token.

Retrieve sequence ids from a token list that has no special tokens added.

For fast tokenizers, data collators call this with `already_has_special_tokens=True` to build a mask over an
already-formatted sequence. In that case, we compute the mask by checking membership in `all_special_ids`.

**Parameters:**

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

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

tokenizer_file (`str`, optional) : Path to a tokenizers JSON file containing the serialization of a tokenizer.

bos_token (`str`, optional, defaults to `""`) : The beginning of sequence token.

eos_token (`str`, optional, defaults to `""`) : The end of sequence token.

sep_token (`str`, optional, defaults to `""`) : The separator token.

cls_token (`str`, optional, defaults to `""`) : The classifier token.

unk_token (`str`, optional, defaults to `""`) : The unknown token.

pad_token (`str`, optional, defaults to `""`) : The padding token.

mask_token (`str`, optional, defaults to `""`) : The mask token.

add_prefix_space (`bool`, optional, defaults to `True`) : Whether to add an initial space.

vocab (`str`, `dict` or `list`, optional) : Custom vocabulary dictionary.

**Returns:**

`A list of integers in the range [0, 1]`

1 for a special token, 0 for a sequence token.
#### save_vocabulary[[transformers.XLMRobertaTokenizer.save_vocabulary]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/tokenization_utils_tokenizers.py#L509)

## XLMRobertaTokenizerFast[[transformers.XLMRobertaTokenizer]]

#### transformers.XLMRobertaTokenizer[[transformers.XLMRobertaTokenizer]]

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

Construct an XLM-RoBERTa tokenizer (backed by HuggingFace's tokenizers library). Based on SentencePiece.

This tokenizer inherits from [TokenizersBackend](/docs/transformers/v5.6.2/en/main_classes/tokenizer#transformers.TokenizersBackend) which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.

**Parameters:**

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

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

tokenizer_file (`str`, optional) : Path to a tokenizers JSON file containing the serialization of a tokenizer.

bos_token (`str`, optional, defaults to `""`) : The beginning of sequence token.

eos_token (`str`, optional, defaults to `""`) : The end of sequence token.

sep_token (`str`, optional, defaults to `""`) : The separator token.

cls_token (`str`, optional, defaults to `""`) : The classifier token.

unk_token (`str`, optional, defaults to `""`) : The unknown token.

pad_token (`str`, optional, defaults to `""`) : The padding token.

mask_token (`str`, optional, defaults to `""`) : The mask token.

add_prefix_space (`bool`, optional, defaults to `True`) : Whether to add an initial space.

vocab (`str`, `dict` or `list`, optional) : Custom vocabulary dictionary.

## XLMRobertaModel[[transformers.XLMRobertaModel]]

#### transformers.XLMRobertaModel[[transformers.XLMRobertaModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L566)

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

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/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.XLMRobertaModel.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L592[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "token_type_ids", "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/v5.6.2/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/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)
- **token_type_ids** (`torch.Tensor` 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.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/v5.6.2/en/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.6.2/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[BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) 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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.
The [XLMRobertaModel](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaModel) 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.
- **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing
  through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns
  the classification token after processing through a linear layer and a tanh activation function. The linear
  layer weights are trained from the next sentence prediction (classification) objective during pretraining.
- **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.
- **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/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.

**Parameters:**

config ([XLMRobertaModel](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaModel)) : 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/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

add_pooling_layer (`bool`, *optional*, defaults to `True`) : Whether to add a pooling layer

**Returns:**

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

A [BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) 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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.

## XLMRobertaForCausalLM[[transformers.XLMRobertaForCausalLM]]

#### transformers.XLMRobertaForCausalLM[[transformers.XLMRobertaForCausalLM]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L698)

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

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/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.XLMRobertaForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L721[{"name": "input_ids", "val": ": torch.LongTensor | 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": "encoder_hidden_states", "val": ": torch.FloatTensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | 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.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/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.

  [What are attention masks?](../glossary#attention-mask)
- **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.
  This parameter can only be used when the model is initialized with `type_vocab_size` parameter with value
  >= 2. All the value in this tensor should be always 0[CausalLMOutputWithCrossAttentions](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithCrossAttentions](/docs/transformers/v5.6.2/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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.
The [XLMRobertaForCausalLM](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForCausalLM) 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/v5.6.2/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, XLMRobertaForCausalLM, AutoConfig
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/roberta-base")
>>> config = AutoConfig.from_pretrained("FacebookAI/roberta-base")
>>> config.is_decoder = True
>>> model = XLMRobertaForCausalLM.from_pretrained("FacebookAI/roberta-base", config=config)

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

>>> prediction_logits = outputs.logits
```

**Parameters:**

config ([XLMRobertaForCausalLM](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForCausalLM)) : 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/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [CausalLMOutputWithCrossAttentions](/docs/transformers/v5.6.2/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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.

## XLMRobertaForMaskedLM[[transformers.XLMRobertaForMaskedLM]]

#### transformers.XLMRobertaForMaskedLM[[transformers.XLMRobertaForMaskedLM]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L806)

The Xlm Roberta Model with a `language modeling` head on top."

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/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.XLMRobertaForMaskedLM.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L833[{"name": "input_ids", "val": ": torch.LongTensor | 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": "encoder_hidden_states", "val": ": torch.FloatTensor | None = None"}, {"name": "encoder_attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | 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/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.

  [What are attention masks?](../glossary#attention-mask)
- **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.
  This parameter can only be used when the model is initialized with `type_vocab_size` parameter with value
  >= 2. All the value in this tensor should be always 0[MaskedLMOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`A [MaskedLMOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) 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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.
The [XLMRobertaForMaskedLM](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForMaskedLM) 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) -- Masked language modeling (MLM) loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
- **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, XLMRobertaForMaskedLM
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/xlm-mlm-en-2048")
>>> model = XLMRobertaForMaskedLM.from_pretrained("FacebookAI/xlm-mlm-en-2048")

>>> inputs = tokenizer("The capital of France is .", return_tensors="pt")

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

>>> # retrieve index of 
>>> mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]

>>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
>>> tokenizer.decode(predicted_token_id)
...

>>> labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"]
>>> # mask labels of non- tokens
>>> labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100)

>>> outputs = model(**inputs, labels=labels)
>>> round(outputs.loss.item(), 2)
...
```

**Parameters:**

config ([XLMRobertaForMaskedLM](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForMaskedLM)) : 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/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [MaskedLMOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) 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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.

## XLMRobertaForSequenceClassification[[transformers.XLMRobertaForSequenceClassification]]

#### transformers.XLMRobertaForSequenceClassification[[transformers.XLMRobertaForSequenceClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L919)

XLM-RoBERTa Model transformer with a sequence classification/regression head on top (a linear layer on top of the
pooled output) e.g. for GLUE tasks.

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/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.XLMRobertaForSequenceClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L931[{"name": "input_ids", "val": ": torch.LongTensor | 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": "**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/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.

  [What are attention masks?](../glossary#attention-mask)
- **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.
  This parameter can only be used when the model is initialized with `type_vocab_size` parameter with value
  >= 2. All the value in this tensor should be always  1` a classification loss is computed (Cross-Entropy).0[SequenceClassifierOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`A [SequenceClassifierOutput](/docs/transformers/v5.6.2/en/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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.
The [XLMRobertaForSequenceClassification](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForSequenceClassification) 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, XLMRobertaForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/xlm-mlm-en-2048")
>>> model = XLMRobertaForSequenceClassification.from_pretrained("FacebookAI/xlm-mlm-en-2048")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

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

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

>>> # 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 = XLMRobertaForSequenceClassification.from_pretrained("FacebookAI/xlm-mlm-en-2048", num_labels=num_labels)

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

Example of multi-label classification:

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

>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/xlm-mlm-en-2048")
>>> model = XLMRobertaForSequenceClassification.from_pretrained("FacebookAI/xlm-mlm-en-2048", problem_type="multi_label_classification")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")

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

>>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze(dim=0) > 0.5]

>>> # 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 = XLMRobertaForSequenceClassification.from_pretrained(
...     "FacebookAI/xlm-mlm-en-2048", num_labels=num_labels, problem_type="multi_label_classification"
... )

>>> labels = torch.sum(
...     torch.nn.functional.one_hot(predicted_class_ids[None, :].clone(), num_classes=num_labels), dim=1
... ).to(torch.float)
>>> loss = model(**inputs, labels=labels).loss
```

**Parameters:**

config ([XLMRobertaForSequenceClassification](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForSequenceClassification)) : 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/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [SequenceClassifierOutput](/docs/transformers/v5.6.2/en/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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.

## XLMRobertaForMultipleChoice[[transformers.XLMRobertaForMultipleChoice]]

#### transformers.XLMRobertaForMultipleChoice[[transformers.XLMRobertaForMultipleChoice]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L1004)

The Xlm Roberta Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a
softmax) e.g. for RocStories/SWAG tasks.

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/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.XLMRobertaForMultipleChoice.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L1015[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "token_type_ids", "val": ": torch.LongTensor | None = None"}, {"name": "attention_mask", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.FloatTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`) --
  Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.6.2/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **token_type_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, 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.
  This parameter can only be used when the model is initialized with `type_vocab_size` parameter with value
  >= 2. All the value in this tensor should be always 0[MultipleChoiceModelOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or `tuple(torch.FloatTensor)`A [MultipleChoiceModelOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) 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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.
The [XLMRobertaForMultipleChoice](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForMultipleChoice) 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, num_choices)`) -- *num_choices* is the second dimension of the input tensors. (see *input_ids* above).

  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.

Example:

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

>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/xlm-mlm-en-2048")
>>> model = XLMRobertaForMultipleChoice.from_pretrained("FacebookAI/xlm-mlm-en-2048")

>>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
>>> choice0 = "It is eaten with a fork and a knife."
>>> choice1 = "It is eaten while held in the hand."
>>> labels = torch.tensor(0).unsqueeze(0)  # choice0 is correct (according to Wikipedia ;)), batch size 1

>>> encoding = tokenizer([prompt, prompt], [choice0, choice1], return_tensors="pt", padding=True)
>>> outputs = model(**{k: v.unsqueeze(0) for k, v in encoding.items()}, labels=labels)  # batch size is 1

>>> # the linear classifier still needs to be trained
>>> loss = outputs.loss
>>> logits = outputs.logits
```

**Parameters:**

config ([XLMRobertaForMultipleChoice](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForMultipleChoice)) : 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/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [MultipleChoiceModelOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) 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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.

## XLMRobertaForTokenClassification[[transformers.XLMRobertaForTokenClassification]]

#### transformers.XLMRobertaForTokenClassification[[transformers.XLMRobertaForTokenClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L1101)

The Xlm Roberta transformer with a token classification head on top (a linear layer on top of the hidden-states
output) e.g. for Named-Entity-Recognition (NER) tasks.

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/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.XLMRobertaForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L1116[{"name": "input_ids", "val": ": torch.LongTensor | 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": "**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/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.

  [What are attention masks?](../glossary#attention-mask)
- **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.
  This parameter can only be used when the model is initialized with `type_vocab_size` parameter with value
  >= 2. All the value in this tensor should be always 0[TokenClassifierOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`A [TokenClassifierOutput](/docs/transformers/v5.6.2/en/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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.
The [XLMRobertaForTokenClassification](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForTokenClassification) 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.

Example:

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

>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/xlm-mlm-en-2048")
>>> model = XLMRobertaForTokenClassification.from_pretrained("FacebookAI/xlm-mlm-en-2048")

>>> inputs = tokenizer(
...     "HuggingFace is a company based in Paris and New York", add_special_tokens=False, return_tensors="pt"
... )

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

>>> predicted_token_class_ids = logits.argmax(-1)

>>> # Note that tokens are classified rather then input words which means that
>>> # there might be more predicted token classes than words.
>>> # Multiple token classes might account for the same word
>>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
>>> predicted_tokens_classes
...

>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).loss
>>> round(loss.item(), 2)
...
```

**Parameters:**

config ([XLMRobertaForTokenClassification](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForTokenClassification)) : 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/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [TokenClassifierOutput](/docs/transformers/v5.6.2/en/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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.

## XLMRobertaForQuestionAnswering[[transformers.XLMRobertaForQuestionAnswering]]

#### transformers.XLMRobertaForQuestionAnswering[[transformers.XLMRobertaForQuestionAnswering]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L1172)

The Xlm Roberta transformer with a span classification head on top for extractive question-answering tasks like
SQuAD (a linear layer on top of the hidden-states output to compute `span start logits` and `span end logits`).

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.2/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.XLMRobertaForQuestionAnswering.forwardhttps://github.com/huggingface/transformers/blob/v5.6.2/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py#L1183[{"name": "input_ids", "val": ": torch.LongTensor | 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": "start_positions", "val": ": torch.LongTensor | None = None"}, {"name": "end_positions", "val": ": torch.LongTensor | 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/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.6.2/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are input IDs?](../glossary#input-ids)
- **attention_mask** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.

  [What are attention masks?](../glossary#attention-mask)
- **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.
  This parameter can only be used when the model is initialized with `type_vocab_size` parameter with value
  >= 2. All the value in this tensor should be always 0[QuestionAnsweringModelOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`A [QuestionAnsweringModelOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) 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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.
The [XLMRobertaForQuestionAnswering](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForQuestionAnswering) 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) -- Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.
- **start_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) -- Span-start scores (before SoftMax).
- **end_logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length)`) -- Span-end 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:

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

>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/xlm-mlm-en-2048")
>>> model = XLMRobertaForQuestionAnswering.from_pretrained("FacebookAI/xlm-mlm-en-2048")

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"

>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> answer_start_index = outputs.start_logits.argmax()
>>> answer_end_index = outputs.end_logits.argmax()

>>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
>>> tokenizer.decode(predict_answer_tokens, skip_special_tokens=True)
...

>>> # target is "nice puppet"
>>> target_start_index = torch.tensor([14])
>>> target_end_index = torch.tensor([15])

>>> outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index)
>>> loss = outputs.loss
>>> round(loss.item(), 2)
...
```

**Parameters:**

config ([XLMRobertaForQuestionAnswering](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaForQuestionAnswering)) : 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/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

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

A [QuestionAnsweringModelOutput](/docs/transformers/v5.6.2/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) 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 ([XLMRobertaConfig](/docs/transformers/v5.6.2/en/model_doc/xlm-roberta#transformers.XLMRobertaConfig)) and inputs.