# GPT NeoX Japanese

## GPT-NeoX-Japanese

### Overview

We introduce GPT-NeoX-Japanese, which is an autoregressive language model for Japanese, trained on top of <https://github.com/EleutherAI/gpt-neox>. Japanese is a unique language with its large vocabulary and a combination of hiragana, katakana, and kanji writing scripts. To address this distinct structure of the Japanese language, we use a [special sub-word tokenizer](https://github.com/tanreinama/Japanese-BPEEncoder_V2). We are very grateful to *tanreinama* for open-sourcing this incredibly helpful tokenizer. Following the recommendations from Google’s research on [PaLM](https://ai.googleblog.com/2022/04/pathways-language-model-palm-scaling-to.html), we have removed bias parameters from transformer blocks, achieving better model performance. Please refer [this article](https://medium.com/ml-abeja/training-a-better-gpt-2-93b157662ae4) in detail.

Development of the model was led by [Shinya Otani](https://github.com/SO0529), [Takayoshi Makabe](https://github.com/spider-man-tm), [Anuj Arora](https://github.com/Anuj040), and [Kyo Hattori](https://github.com/go5paopao) from [ABEJA, Inc.](https://www.abejainc.com/). For more information on this model-building activity, please refer [here (ja)](https://tech-blog.abeja.asia/entry/abeja-gpt-project-202207).

#### Generation

The `generate()` method can be used to generate text using GPT NeoX Japanese model.

Copied

```
>>> from transformers import GPTNeoXJapaneseForCausalLM, GPTNeoXJapaneseTokenizer

>>> model = GPTNeoXJapaneseForCausalLM.from_pretrained("abeja/gpt-neox-japanese-2.7b")
>>> tokenizer = GPTNeoXJapaneseTokenizer.from_pretrained("abeja/gpt-neox-japanese-2.7b")

>>> prompt = "人とAIが協調するためには、"

>>> input_ids = tokenizer(prompt, return_tensors="pt").input_ids

>>> gen_tokens = model.generate(
...     input_ids,
...     do_sample=True,
...     temperature=0.9,
...     max_length=100,
... )
>>> gen_text = tokenizer.batch_decode(gen_tokens, skip_special_tokens=True)[0]

>>> print(gen_text)
人とAIが協調するためには、AIと人が共存し、AIを正しく理解する必要があります。
```

### Documentation resources

* [Causal language modeling task guide](https://huggingface.co/docs/transformers/tasks/language_modeling)

### GPTNeoXJapaneseConfig

#### class transformers.GPTNeoXJapaneseConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/gpt_neox_japanese/configuration_gpt_neox_japanese.py#L28)

( vocab\_size = 32000hidden\_size = 2560num\_hidden\_layers = 32num\_attention\_heads = 32intermediate\_multiple\_size = 4hidden\_act = 'gelu'rotary\_pct = 1.0rotary\_emb\_base = 10000max\_position\_embeddings = 2048initializer\_range = 0.02layer\_norm\_eps = 1e-05use\_cache = Truebos\_token\_id = 31996eos\_token\_id = 31999attention\_dropout = 0.1hidden\_dropout = 0.0\*\*kwargs )

Parameters

* **vocab\_size** (`int`, *optional*, defaults to 32000) — Vocabulary size of the GPTNeoXJapanese model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling `GPTNeoXJapanese`.
* **hidden\_size** (`int`, *optional*, defaults to 2560) — Dimension of the encoder layers and the pooler layer.
* **num\_hidden\_layers** (`int`, *optional*, defaults to 32) — Number of hidden layers in the Transformer encoder.
* **num\_attention\_heads** (`int`, *optional*, defaults to 32) — Number of attention heads for each attention layer in the Transformer encoder.
* **intermediate\_multiple\_size** (`int`, *optional*, defaults to 4) — Dimension of the “intermediate” layer in the Transformer encoder is calculated by hidden\_size \* intermediate\_multiple\_size.
* **hidden\_act** (`str` or `function`, *optional*, defaults to `"gelu"`) — The non-linear activation function (function or string) in the encoder and pooler.
* **rotary\_pct** (`float`, *optional*, defaults to 1.00) — percentage of hidden dimensions to allocate to rotary embeddings
* **rotary\_emb\_base** (`int`, *optional*, defaults to 10000) — base for computing rotary embeddings frequency
* **max\_position\_embeddings** (`int`, *optional*, defaults to 2048) — The maximum sequence length that this model might ever be used with.
* **initializer\_range** (`float`, *optional*, defaults to 0.02) — The standard deviation of the truncated\_normal\_initializer for initializing all weight matrices.
* **layer\_norm\_eps** (`float`, *optional*, defaults to 1e-5) — The epsilon used by the layer normalization layers.
* **use\_cache** (`bool`, *optional*, defaults to `True`) — Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`.
* **attention\_dropout** (`float`, *optional*, defaults to 0.1) — The dropout ratio for the attention.
* **hidden\_dropout** (`float`, *optional*, defaults to 0.0) — The dropout ratio for the hidden layer. Example —

This is the configuration class to store the configuration of a `GPTNeoXModelJapanese`. It is used to instantiate a GPTNeoX 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 GPTNeoXJapanese [abeja/gpt-neox-japanese-2.7b](https://huggingface.co/abeja/gpt-neox-japanese-2.7b) architecture.

Configuration objects inherit from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) for more information. Default configs is set as 2.7B model

Copied

```
>>> from transformers import GPTNeoXJapaneseConfig, GPTNeoXJapaneseModel

>>> # Initializing a GPTNeoXJapanese gpt-neox-japanese-2.7b style configuration
>>> configuration = GPTNeoXJapaneseConfig()

>>> # Initializing a model (with random weights) from the gpt-neox-japanese-2.7b style configuration
>>> model = GPTNeoXJapaneseModel(configuration)

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

### GPTNeoXJapaneseTokenizer

#### class transformers.GPTNeoXJapaneseTokenizer

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/gpt_neox_japanese/tokenization_gpt_neox_japanese.py#L66)

( vocab\_fileemoji\_fileunk\_token = '<|endoftext|>'pad\_token = '<|endoftext|>'bos\_token = '<|startoftext|>'eos\_token = '<|endoftext|>'do\_clean\_text = False\*\*kwargs )

Parameters

* **vocab\_file** (`str`) — File containing the vocabulary.
* **emoji\_file** (`str`) — File containing the emoji.
* **unk\_token** (`str`, *optional*, defaults to `"<|endoftext|>"`) — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
* **pad\_token** (`str`, *optional*, defaults to `"<|endoftext|>"`) — The token used for padding
* **bos\_token** (`str`, *optional*, defaults to `"<|startoftext|>"`) — The beginning of sequence token.
* **eos\_token** (`str`, *optional*, defaults to `"<|endoftext|>"`) — The end of sequence token.
* **do\_clean\_text** (`bool`, *optional*, defaults to `False`) — Whether or not to clean text for URL, EMAIL, TEL, Japanese DATE and Japanese PRICE.

This tokenizer inherits from [PreTrainedTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizer) and is based on Japanese special Sub-Word-Encoding that is used in this repository (<https://github.com/tanreinama/Japanese-BPEEncoder_V2>). Check the repository for details. Japanese has a relatively large vocabulary and there is no separation between words. Furthermore, the language is a combination of hiragana, katakana, and kanji, and variants such as “1” and “①” are often used. In order to cope with these, this tokenizer has the following features

* Subword-by-subword segmentation, which is intermediate between byte strings and morphological analysis.
* BPEs are created for each Kanji, Hiragana, and Katakana character, and there are no BPEs that cross character types, such as Kanji + Hiragana or Hiragana + Katakana.
* All-byte encoding that does not require \<unk>.
* Independent of UTF codes such as 2-byte and 3-byte characters
* Conversion of heterographs to the same token\_id
* Emoji and Emoticon are grouped into 12 types as special tags.

Example:

Copied

```
>>> from transformers import GPTNeoXJapaneseTokenizer

>>> tokenizer = GPTNeoXJapaneseTokenizer.from_pretrained("abeja/gpt-neox-japanese-2.7b")
>>> # You can confirm both 慶応 and 慶應 are encoded to 17749
>>> tokenizer("吾輩は猫である🐯。実は慶応(慶應)大学出身")["input_ids"]
[30014, 26883, 26638, 27228, 25, 26650, 31732, 31679, 27809, 26638, 17749, 31592, 17749, 31593, 321, 1281]

>>> # Both 慶応 and 慶應 are decoded to 慶応
>>> tokenizer.decode(tokenizer("吾輩は猫である🐯。実は慶応(慶應)大学出身")["input_ids"])
'吾輩は猫である🐯。実は慶応(慶応)大学出身'
```

**convert\_tokens\_to\_string**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/gpt_neox_japanese/tokenization_gpt_neox_japanese.py#L173)

( tokens )

Converts a sequence of tokens (string) in a single string.

### GPTNeoXJapaneseModel

#### class transformers.GPTNeoXJapaneseModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py#L440)

( config )

Parameters

* **config** ([\~GPTNeoXJapaneseConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/gpt_neox_japanese#transformers.GPTNeoXJapaneseConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

The bare GPTNeoXJapanese Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py#L460)

( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonepast\_key\_values: typing.Optional\[typing.Tuple\[typing.Tuple\[torch.FloatTensor]]] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.BaseModelOutputWithPast](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer).
* **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**.
* **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.
* **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.max_position_embeddings - 1]`.
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **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.
* **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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`) — Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_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`).

Returns

[transformers.modeling\_outputs.BaseModelOutputWithPast](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.BaseModelOutputWithPast](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([GPTNeoXJapaneseConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/gpt_neox_japanese#transformers.GPTNeoXJapaneseConfig)) and inputs.

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

  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1, hidden_size)` is output.
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and optionally if `config.is_encoder_decoder=True` 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`.

  Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [GPTNeoXJapaneseModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/gpt_neox_japanese#transformers.GPTNeoXJapaneseModel) 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.

Example:

Copied

```
>>> from transformers import AutoTokenizer, GPTNeoXJapaneseModel
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("abeja/gpt-neox-japanese-2.7b")
>>> model = GPTNeoXJapaneseModel.from_pretrained("abeja/gpt-neox-japanese-2.7b")

>>> inputs = tokenizer("日本語のGPT-neoxがBOINC AIで使えます😀", return_tensors="pt")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
```

### GPTNeoXJapaneseForCausalLM

#### class transformers.GPTNeoXJapaneseForCausalLM

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py#L595)

( config )

Parameters

* **config** ([\~GPTNeoXJapaneseConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/gpt_neox_japanese#transformers.GPTNeoXJapaneseConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

GPTNeoXJapanese Model with a `language modeling` head on top for Classifier Model fine-tuning. This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/gpt_neox_japanese/modeling_gpt_neox_japanese.py#L614)

( input\_ids: typing.Optional\[torch.LongTensor] = Noneattention\_mask: typing.Optional\[torch.FloatTensor] = Noneinputs\_embeds: typing.Optional\[torch.FloatTensor] = Nonehead\_mask: typing.Optional\[torch.FloatTensor] = Nonepast\_key\_values: typing.Optional\[typing.Tuple\[typing.Tuple\[torch.FloatTensor]]] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneuse\_cache: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.CausalLMOutputWithPast](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)`

Parameters

* **input\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`) — Indices of input sequence tokens in the vocabulary.

  Indices can be obtained using [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer).
* **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**.
* **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.
* **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.max_position_embeddings - 1]`.
* **head\_mask** (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*) — Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
  * 1 indicates the head is **not masked**,
  * 0 indicates the head is **masked**.
* **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.
* **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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. The two additional tensors are only required when the model is used as a decoder in a Sequence to Sequence model.

  Contains pre-computed hidden-states (key and values in the self-attention blocks that can be used (see `past_key_values` input) to speed up sequential decoding.

  If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don’t have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
* **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]`.
* **use\_cache** (`bool`, *optional*) — If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`).

Returns

[transformers.modeling\_outputs.CausalLMOutputWithPast](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.CausalLMOutputWithPast](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([GPTNeoXJapaneseConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/gpt_neox_japanese#transformers.GPTNeoXJapaneseConfig)) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) — Language modeling loss (for next-token prediction).
* **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
* **past\_key\_values** (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) — Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`)

  Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [GPTNeoXJapaneseForCausalLM](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/gpt_neox_japanese#transformers.GPTNeoXJapaneseForCausalLM) 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.

Example:

Copied

```
>>> from transformers import AutoTokenizer, GPTNeoXJapaneseForCausalLM, GPTNeoXJapaneseConfig
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("abeja/gpt-neox-japanese-2.7b")
>>> config = GPTNeoXJapaneseConfig.from_pretrained("abeja/gpt-neox-japanese-2.7b")
>>> config.is_decoder = True
>>> model = GPTNeoXJapaneseForCausalLM.from_pretrained("abeja/gpt-neox-japanese-2.7b", config=config)

>>> inputs = tokenizer("日本語のGPT-neoxがBOINC AIで使えます😀", return_tensors="pt")
>>> outputs = model(**inputs)

>>> prediction_logits = outputs.logits
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://boinc-ai.gitbook.io/transformers/api/models/text-models/gpt-neox-japanese.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.