# MegatronBERT

## Overview

The MegatronBERT model was proposed in [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model
Parallelism](https://huggingface.co/papers/1909.08053) by Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley,
Jared Casper and Bryan Catanzaro.

The abstract from the paper is the following:

*Recent work in language modeling demonstrates that training large transformer models advances the state of the art in
Natural Language Processing applications. However, very large models can be quite difficult to train due to memory
constraints. In this work, we present our techniques for training very large transformer models and implement a simple,
efficient intra-layer model parallel approach that enables training transformer models with billions of parameters. Our
approach does not require a new compiler or library changes, is orthogonal and complimentary to pipeline model
parallelism, and can be fully implemented with the insertion of a few communication operations in native PyTorch. We
illustrate this approach by converging transformer based models up to 8.3 billion parameters using 512 GPUs. We sustain
15.1 PetaFLOPs across the entire application with 76% scaling efficiency when compared to a strong single GPU baseline
that sustains 39 TeraFLOPs, which is 30% of peak FLOPs. To demonstrate that large language models can further advance
the state of the art (SOTA), we train an 8.3 billion parameter transformer language model similar to GPT-2 and a 3.9
billion parameter model similar to BERT. We show that careful attention to the placement of layer normalization in
BERT-like models is critical to achieving increased performance as the model size grows. Using the GPT-2 model we
achieve SOTA results on the WikiText103 (10.8 compared to SOTA perplexity of 15.8) and LAMBADA (66.5% compared to SOTA
accuracy of 63.2%) datasets. Our BERT model achieves SOTA results on the RACE dataset (90.9% compared to SOTA accuracy
of 89.4%).*

This model was contributed by [jdemouth](https://huggingface.co/jdemouth). The original code can be found [here](https://github.com/NVIDIA/Megatron-LM).
That repository contains a multi-GPU and multi-node implementation of the Megatron Language models. In particular,
it contains a hybrid model parallel approach using "tensor parallel" and "pipeline parallel" techniques.

## Usage tips

We have provided pretrained [BERT-345M](https://ngc.nvidia.com/catalog/models/nvidia:megatron_bert_345m) checkpoints
for use to evaluate or finetuning downstream tasks.

To access these checkpoints, first [sign up](https://ngc.nvidia.com/signup) for and setup the NVIDIA GPU Cloud (NGC)
Registry CLI. Further documentation for downloading models can be found in the [NGC documentation](https://docs.nvidia.com/dgx/ngc-registry-cli-user-guide/index.html#topic_6_4_1).

Alternatively, you can directly download the checkpoints using:

BERT-345M-uncased:

```bash
wget --content-disposition https://api.ngc.nvidia.com/v2/models/nvidia/megatron_bert_345m/versions/v0.1_uncased/zip
-O megatron_bert_345m_v0_1_uncased.zip
```

BERT-345M-cased:

```bash
wget --content-disposition https://api.ngc.nvidia.com/v2/models/nvidia/megatron_bert_345m/versions/v0.1_cased/zip -O
megatron_bert_345m_v0_1_cased.zip
```

Once you have obtained the checkpoints from NVIDIA GPU Cloud (NGC), you have to convert them to a format that will
easily be loaded by Hugging Face Transformers and our port of the BERT code.

The following commands allow you to do the conversion. We assume that the folder `models/megatron_bert` contains
`megatron_bert_345m_v0_1_{cased, uncased}.zip` and that the commands are run from inside that folder:

```bash
python3 $PATH_TO_TRANSFORMERS/models/megatron_bert/convert_megatron_bert_checkpoint.py megatron_bert_345m_v0_1_uncased.zip
```

```bash
python3 $PATH_TO_TRANSFORMERS/models/megatron_bert/convert_megatron_bert_checkpoint.py megatron_bert_345m_v0_1_cased.zip
```

## Resources

- [Text classification task guide](../tasks/sequence_classification)
- [Token classification task guide](../tasks/token_classification)
- [Question answering task guide](../tasks/question_answering)
- [Causal language modeling task guide](../tasks/language_modeling)
- [Masked language modeling task guide](../tasks/masked_language_modeling)
- [Multiple choice task guide](../tasks/multiple_choice)

## MegatronBertConfig[[transformers.MegatronBertConfig]]

#### transformers.MegatronBertConfig[[transformers.MegatronBertConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/configuration_megatron_bert.py#L24)

This is the configuration class to store the configuration of a Megatron BertModel. It is used to instantiate a Megatron Bert
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 [nvidia/megatron-bert-uncased-345m](https://huggingface.co/nvidia/megatron-bert-uncased-345m)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Examples:

```python
>>> from transformers import MegatronBertConfig, MegatronBertModel

>>> # Initializing a MEGATRON_BERT google-bert/bert-base-uncased style configuration
>>> configuration = MegatronBertConfig()

>>> # Initializing a model (with random weights) from the google-bert/bert-base-uncased style configuration
>>> model = MegatronBertModel(configuration)

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

**Parameters:**

vocab_size (`int`, *optional*, defaults to `29056`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`.

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

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

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

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

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

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

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

max_position_embeddings (`int`, *optional*, defaults to `512`) : The maximum sequence length that this model might ever be used with.

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

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

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

use_cache (`bool`, *optional*, defaults to `True`) : Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True` or when the model is a decoder-only generative model.

is_decoder (`bool`, *optional*, defaults to `False`) : Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.

add_cross_attention (`bool`, *optional*, defaults to `False`) : Whether cross-attention layers should be added to the model.

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

## MegatronBertModel[[transformers.MegatronBertModel]]

#### transformers.MegatronBertModel[[transformers.MegatronBertModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L547)

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

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.MegatronBertModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L582[{"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": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **encoder_hidden_states** (`torch.FloatTensor` 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.FloatTensor` 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/v5.8.0/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/v5.8.0/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`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertModel](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertModel) 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/v5.8.0/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 ([MegatronBertModel](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertModel)) : 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/v5.8.0/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/v5.8.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPoolingAndCrossAttentions) or `tuple(torch.FloatTensor)``

A [BaseModelOutputWithPoolingAndCrossAttentions](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.

## MegatronBertForMaskedLM[[transformers.MegatronBertForMaskedLM]]

#### transformers.MegatronBertForMaskedLM[[transformers.MegatronBertForMaskedLM]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L901)

The Megatron Bert Model with a `language modeling` head on top."

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.MegatronBertForMaskedLM.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L929[{"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": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **encoder_hidden_states** (`torch.FloatTensor` 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.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
  the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
  config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the
  loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[MaskedLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`A [MaskedLMOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertForMaskedLM](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForMaskedLM) 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, MegatronBertForMaskedLM
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-uncased-345m")
>>> model = MegatronBertForMaskedLM.from_pretrained("nvidia/megatron-bert-uncased-345m")

>>> 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 ([MegatronBertForMaskedLM](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForMaskedLM)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[MaskedLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)``

A [MaskedLMOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.

## MegatronBertForCausalLM[[transformers.MegatronBertForCausalLM]]

#### transformers.MegatronBertForCausalLM[[transformers.MegatronBertForCausalLM]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L794)

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

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.MegatronBertForCausalLM.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L819[{"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": ": transformers.cache_utils.Cache | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "logits_to_keep", "val": ": int | torch.Tensor = 0"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **encoder_hidden_states** (`torch.FloatTensor` 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.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
  the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.
- **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
  `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
  ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`
- **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/v5.8.0/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/v5.8.0/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`).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
- **logits_to_keep** (`Union[int, torch.Tensor]`, *optional*, defaults to `0`) --
  If an `int`, compute logits for the last `logits_to_keep` tokens. If `0`, calculate logits for all
  `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that
  token can save memory, which becomes pretty significant for long sequences or large vocabulary size.
  If a `torch.Tensor`, must be 1D corresponding to the indices to keep in the sequence length dimension.
  This is useful when using packed tensor format (single dimension for batch and sequence length).0[CausalLMOutputWithCrossAttentions](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)`A [CausalLMOutputWithCrossAttentions](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertForCausalLM](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForCausalLM) 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/v5.8.0/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, MegatronBertForCausalLM, MegatronBertConfig
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-cased-345m")
>>> model = MegatronBertForCausalLM.from_pretrained("nvidia/megatron-bert-cased-345m", is_decoder=True)

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

>>> prediction_logits = outputs.logits
```

**Parameters:**

config ([MegatronBertForCausalLM](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForCausalLM)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[CausalLMOutputWithCrossAttentions](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithCrossAttentions) or `tuple(torch.FloatTensor)``

A [CausalLMOutputWithCrossAttentions](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.

## MegatronBertForNextSentencePrediction[[transformers.MegatronBertForNextSentencePrediction]]

#### transformers.MegatronBertForNextSentencePrediction[[transformers.MegatronBertForNextSentencePrediction]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L992)

MegatronBert Model with a `next sentence prediction (classification)` head on top.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.MegatronBertForNextSentencePrediction.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1002[{"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": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair
  (see `input_ids` docstring). Indices should be in `[0, 1]`:

  - 0 indicates sequence B is a continuation of sequence A,
  - 1 indicates sequence B is a random sequence.
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[NextSentencePredictorOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.NextSentencePredictorOutput) or `tuple(torch.FloatTensor)`A [NextSentencePredictorOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.NextSentencePredictorOutput) 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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertForNextSentencePrediction](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForNextSentencePrediction) 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 `next_sentence_label` is provided) -- Next sequence prediction (classification) loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, 2)`) -- Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation
  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, MegatronBertForNextSentencePrediction
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-cased-345m")
>>> model = MegatronBertForNextSentencePrediction.from_pretrained("nvidia/megatron-bert-cased-345m")

>>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
>>> next_sentence = "The sky is blue due to the shorter wavelength of blue light."
>>> encoding = tokenizer(prompt, next_sentence, return_tensors="pt")

>>> outputs = model(**encoding, labels=torch.LongTensor([1]))
>>> logits = outputs.logits
>>> assert logits[0, 0] 

**Parameters:**

config ([MegatronBertForNextSentencePrediction](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForNextSentencePrediction)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[NextSentencePredictorOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.NextSentencePredictorOutput) or `tuple(torch.FloatTensor)``

A [NextSentencePredictorOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.NextSentencePredictorOutput) 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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.</div>

## MegatronBertForPreTraining[[transformers.MegatronBertForPreTraining]]

#### transformers.MegatronBertForPreTraining[[transformers.MegatronBertForPreTraining]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L685)

MegatronBert Model with two heads on top as done during the pretraining: a `masked language modeling` head and a
`next sentence prediction (classification)` head.

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/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.MegatronBertForPreTraining.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L711[{"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": "next_sentence_label", "val": ": torch.LongTensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
  config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the
  loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
- **next_sentence_label** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair
  (see `input_ids` docstring) Indices should be in `[0, 1]`:

  - 0 indicates sequence B is a continuation of sequence A,
  - 1 indicates sequence B is a random sequence.
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0`MegatronBertForPreTrainingOutput` or `tuple(torch.FloatTensor)`A `MegatronBertForPreTrainingOutput` 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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertForPreTraining](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForPreTraining) 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** (`*optional*`, returned when `labels` is provided, `torch.FloatTensor` of shape `(1,)`) -- Total loss as the sum of the masked language modeling loss and the next sequence prediction
  (classification) loss.
- **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).
- **seq_relationship_logits** (`torch.FloatTensor` of shape `(batch_size, 2)`) -- Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation
  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, MegatronBertForPreTraining
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-cased-345m")
>>> model = MegatronBertForPreTraining.from_pretrained("nvidia/megatron-bert-cased-345m")

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

>>> prediction_logits = outputs.prediction_logits
>>> seq_relationship_logits = outputs.seq_relationship_logits
```

**Parameters:**

config ([MegatronBertForPreTraining](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForPreTraining)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

add_binary_head (`bool`, *optional*, defaults to `True`) : Whether or not to add a binary head.

**Returns:**

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

A `MegatronBertForPreTrainingOutput` 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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.</div>

## MegatronBertForSequenceClassification[[transformers.MegatronBertForSequenceClassification]]

#### transformers.MegatronBertForSequenceClassification[[transformers.MegatronBertForSequenceClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1082)

MegatronBert 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/v5.8.0/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.MegatronBertForSequenceClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1094[{"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": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
  config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
  `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[SequenceClassifierOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`A [SequenceClassifierOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertForSequenceClassification](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForSequenceClassification) 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, MegatronBertForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-uncased-345m")
>>> model = MegatronBertForSequenceClassification.from_pretrained("nvidia/megatron-bert-uncased-345m")

>>> 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 = MegatronBertForSequenceClassification.from_pretrained("nvidia/megatron-bert-uncased-345m", 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, MegatronBertForSequenceClassification

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-uncased-345m")
>>> model = MegatronBertForSequenceClassification.from_pretrained("nvidia/megatron-bert-uncased-345m", 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 = MegatronBertForSequenceClassification.from_pretrained(
...     "nvidia/megatron-bert-uncased-345m", 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 ([MegatronBertForSequenceClassification](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForSequenceClassification)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[SequenceClassifierOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)``

A [SequenceClassifierOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.</div>

## MegatronBertForMultipleChoice[[transformers.MegatronBertForMultipleChoice]]

#### transformers.MegatronBertForMultipleChoice[[transformers.MegatronBertForMultipleChoice]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1167)

The Megatron Bert 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/v5.8.0/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.MegatronBertForMultipleChoice.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1178[{"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": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`) --
  Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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, 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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, num_choices, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
  num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See
  `input_ids` above)
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[MultipleChoiceModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or `tuple(torch.FloatTensor)`A [MultipleChoiceModelOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertForMultipleChoice](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForMultipleChoice) 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, MegatronBertForMultipleChoice
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-uncased-345m")
>>> model = MegatronBertForMultipleChoice.from_pretrained("nvidia/megatron-bert-uncased-345m")

>>> 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 ([MegatronBertForMultipleChoice](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForMultipleChoice)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[MultipleChoiceModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.MultipleChoiceModelOutput) or `tuple(torch.FloatTensor)``

A [MultipleChoiceModelOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.</div>

## MegatronBertForTokenClassification[[transformers.MegatronBertForTokenClassification]]

#### transformers.MegatronBertForTokenClassification[[transformers.MegatronBertForTokenClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1270)

The Megatron Bert 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/v5.8.0/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.MegatronBertForTokenClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1282[{"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": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[TokenClassifierOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)`A [TokenClassifierOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertForTokenClassification](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForTokenClassification) 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, MegatronBertForTokenClassification
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-uncased-345m")
>>> model = MegatronBertForTokenClassification.from_pretrained("nvidia/megatron-bert-uncased-345m")

>>> 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 ([MegatronBertForTokenClassification](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForTokenClassification)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[TokenClassifierOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.TokenClassifierOutput) or `tuple(torch.FloatTensor)``

A [TokenClassifierOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.</div>

## MegatronBertForQuestionAnswering[[transformers.MegatronBertForQuestionAnswering]]

#### transformers.MegatronBertForQuestionAnswering[[transformers.MegatronBertForQuestionAnswering]]

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1336)

The Megatron Bert 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/v5.8.0/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.MegatronBertForQuestionAnswering.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/megatron_bert/modeling_megatron_bert.py#L1347[{"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": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

  Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/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.

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

  [What are position IDs?](../glossary#position-ids)
- **inputs_embeds** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.
- **start_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for position (index) of the start of the labelled span for computing the token classification loss.
  Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
  are not taken into account for computing the loss.
- **end_positions** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for position (index) of the end of the labelled span for computing the token classification loss.
  Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
  are not taken into account for computing the loss.
- **output_attentions** (`bool`, *optional*) --
  Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
  tensors for more detail.
- **output_hidden_states** (`bool`, *optional*) --
  Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
  more detail.
- **return_dict** (`bool`, *optional*) --
  Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[QuestionAnsweringModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)`A [QuestionAnsweringModelOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.
The [MegatronBertForQuestionAnswering](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForQuestionAnswering) 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, MegatronBertForQuestionAnswering
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("nvidia/megatron-bert-uncased-345m")
>>> model = MegatronBertForQuestionAnswering.from_pretrained("nvidia/megatron-bert-uncased-345m")

>>> 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 ([MegatronBertForQuestionAnswering](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertForQuestionAnswering)) : 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/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[QuestionAnsweringModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.QuestionAnsweringModelOutput) or `tuple(torch.FloatTensor)``

A [QuestionAnsweringModelOutput](/docs/transformers/v5.8.0/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 ([MegatronBertConfig](/docs/transformers/v5.8.0/en/model_doc/megatron-bert#transformers.MegatronBertConfig)) and inputs.