Hugging Face's logo

Transformers documentation

GPT-NeoX

You are viewing v4.27.2 version. A newer version v4.46.3 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

GPT-NeoX

Overview

We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive language model trained on the Pile, whose weights will be made freely and openly available to the public through a permissive license. It is, to the best of our knowledge, the largest dense autoregressive model that has publicly available weights at the time of submission. In this work, we describe GPT-NeoX-20B’s architecture and training and evaluate its performance on a range of language-understanding, mathematics, and knowledge-based tasks. We find that GPT-NeoX-20B is a particularly powerful few-shot reasoner and gains far more in performance when evaluated five-shot than similarly sized GPT-3 and FairSeq models. We open-source the training and evaluation code, as well as the model weights, at https://github.com/EleutherAI/gpt-neox.

Development of the model was led by Sid Black, Stella Biderman and Eric Hallahan, and the model was trained with generous the support of CoreWeave.

GPT-NeoX-20B was trained with fp16, thus it is recommended to initialize the model as follows:

model = GPTNeoXForCausalLM.from_pretrained("EleutherAI/gpt-neox-20b").half().cuda()

GPT-NeoX-20B also has a different tokenizer from the one used in GPT-J-6B and GPT-Neo. The new tokenizer allocates additional tokens to whitespace characters, making the model more suitable for certain tasks like code generation.

Generation

The generate() method can be used to generate text using GPT Neo model.

>>> from transformers import GPTNeoXForCausalLM, GPTNeoXTokenizerFast

>>> model = GPTNeoXForCausalLM.from_pretrained("EleutherAI/gpt-neox-20b")
>>> tokenizer = GPTNeoXTokenizerFast.from_pretrained("EleutherAI/gpt-neox-20b")

>>> prompt = "GPTNeoX20B is a 20B-parameter autoregressive Transformer model developed by EleutherAI."

>>> 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)[0]

Documentation resources

GPTNeoXConfig

class transformers.GPTNeoXConfig

< >

( vocab_size = 50432 hidden_size = 6144 num_hidden_layers = 44 num_attention_heads = 64 intermediate_size = 24576 hidden_act = 'gelu' rotary_pct = 0.25 rotary_emb_base = 10000 max_position_embeddings = 2048 initializer_range = 0.02 layer_norm_eps = 1e-05 use_cache = True bos_token_id = 0 eos_token_id = 2 tie_word_embeddings = False use_parallel_residual = True **kwargs )

Parameters

  • vocab_size (int, optional, defaults to 50432) — Vocabulary size of the GPTNeoX model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling GPTNeoXModel.
  • hidden_size (int, optional, defaults to 6144) — Dimension of the encoder layers and the pooler layer.
  • num_hidden_layers (int, optional, defaults to 44) — Number of hidden layers in the Transformer encoder.
  • num_attention_heads (int, optional, defaults to 64) — Number of attention heads for each attention layer in the Transformer encoder.
  • intermediate_size (int, optional, defaults to 24576) — Dimension of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
  • hidden_act (str or function, optional, defaults to "gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" are supported.
  • rotary_pct (float, optional, defaults to 0.25) — 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. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
  • initializer_range (float, optional, defaults to 1e-5) — 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.
  • 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.
  • use_parallel_residual (bool, optional, defaults to True) — Whether to use a “parallel” formulation in each Transformer layer, which can provide a slight training speedup at large scales (e.g. 20B). Example —

This is the configuration class to store the configuration of a GPTNeoXModel. It is used to instantiate an 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 GPTNeoX EleutherAI/gpt-neox-20b architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

>>> from transformers import GPTNeoXConfig, GPTNeoXModel

>>> # Initializing a GPTNeoX gpt-neox-20b style configuration
>>> configuration = GPTNeoXConfig()

>>> # Initializing a model (with random weights) from the gpt-neox-20b style configuration
>>> model = GPTNeoXModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config

GPTNeoXTokenizerFast

class transformers.GPTNeoXTokenizerFast

< >

( vocab_file = None merges_file = None tokenizer_file = None unk_token = '<|endoftext|>' bos_token = '<|endoftext|>' eos_token = '<|endoftext|>' add_prefix_space = False **kwargs )

Parameters

  • vocab_file (str) — Path to the vocabulary file.
  • merges_file (str) — Path to the merges file.
  • errors (str, optional, defaults to "replace") — Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information.
  • 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.
  • bos_token (str, optional, defaults to <|endoftext|>) — The beginning of sequence token.
  • eos_token (str, optional, defaults to <|endoftext|>) — The end of sequence token.
  • add_prefix_space (bool, optional, defaults to False) — Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (GPTNeoX tokenizer detect beginning of words by the preceding space).
  • trim_offsets (bool, optional, defaults to True) — Whether or not the post-processing step should trim offsets to avoid including whitespaces.

Construct a “fast” GPT-NeoX-20B tokenizer (backed by HuggingFace’s tokenizers library). Based on byte-level Byte-Pair-Encoding.

This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will

be encoded differently whether it is at the beginning of the sentence (without space) or not:

>>> from transformers import GPTNeoXTokenizerFast
>>> tokenizer = GPTNeoXTokenizerFast.from_pretrained("gpt2")
>>> tokenizer("Hello world")['input_ids']
[15496, 995]
>>> tokenizer(" Hello world")['input_ids']
[18435, 995]

You can get around that behavior by passing add_prefix_space=True when instantiating this tokenizer, but since the model was not pretrained this way, it might yield a decrease in performance.

When used with is_split_into_words=True, this tokenizer needs to be instantiated with add_prefix_space=True.

This tokenizer inherits from PreTrainedTokenizerFast which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

GPTNeoXModel

class transformers.GPTNeoXModel

< >

( config )

Parameters

  • config (~GPTNeoXConfig) — 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() method to load the model weights.

The bare GPTNeoX Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch 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

< >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → 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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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 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 or tuple(torch.FloatTensor)

A 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 (GPTNeoXConfig) 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 GPTNeoXModel 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.

This example uses a random model as the real ones are all very big. To get proper results, you should use EleutherAI/gpt-neox-20b instead of trl-internal-testing/tiny-random-GPTNeoXForCausalLM. If you get out-of-memory when loading that checkpoint, you can try adding device_map="auto" in the from_pretrained call.

Example:

>>> from transformers import AutoTokenizer, GPTNeoXModel
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-random-GPTNeoXForCausalLM")
>>> model = GPTNeoXModel.from_pretrained("trl-internal-testing/tiny-random-GPTNeoXForCausalLM")

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

>>> last_hidden_states = outputs.last_hidden_state

GPTNeoXForCausalLM

class transformers.GPTNeoXForCausalLM

< >

( config )

Parameters

  • config (~GPTNeoXConfig) — 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() method to load the model weights.

GPTNeoX Model with a language modeling head on top for CLM fine-tuning. This model is a PyTorch 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

< >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None past_key_values: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → 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. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are 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?

  • 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 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 or tuple(torch.FloatTensor)

A 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 (GPTNeoXConfig) 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 GPTNeoXForCausalLM 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:

>>> from transformers import AutoTokenizer, GPTNeoXForCausalLM, GPTNeoXConfig
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
>>> config = GPTNeoXConfig.from_pretrained("EleutherAI/gpt-neox-20b")
>>> config.is_decoder = True
>>> model = GPTNeoXForCausalLM.from_pretrained("EleutherAI/gpt-neox-20b", config=config)

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

>>> prediction_logits = outputs.logits
←GPT Neo GPT NeoX Japanese→