Hugging Face's logo

Transformers documentation

JetMoe

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v4.47.1).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

JetMoe

Overview

JetMoe-8B is an 8B Mixture-of-Experts (MoE) language model developed by Yikang Shen and MyShell. JetMoe project aims to provide a LLaMA2-level performance and efficient language model with a limited budget. To achieve this goal, JetMoe uses a sparsely activated architecture inspired by the ModuleFormer. Each JetMoe block consists of two MoE layers: Mixture of Attention Heads and Mixture of MLP Experts. Given the input tokens, it activates a subset of its experts to process them. This sparse activation schema enables JetMoe to achieve much better training throughput than similar size dense models. The training throughput of JetMoe-8B is around 100B tokens per day on a cluster of 96 H100 GPUs with a straightforward 3-way pipeline parallelism strategy.

This model was contributed by Yikang Shen.

JetMoeConfig

class transformers.JetMoeConfig

< >

( vocab_size = 32000 hidden_size = 2048 num_hidden_layers = 12 num_key_value_heads = 16 kv_channels = 128 intermediate_size = 5632 max_position_embeddings = 4096 activation_function = 'silu' num_local_experts = 8 num_experts_per_tok = 2 output_router_logits = False aux_loss_coef = 0.01 use_cache = True bos_token_id = 1 eos_token_id = 2 tie_word_embeddings = True rope_theta = 10000.0 rms_norm_eps = 1e-06 initializer_range = 0.01 attention_dropout = 0.0 **kwargs )

Parameters

  • vocab_size (int, optional, defaults to 32000) — Vocabulary size of the JetMoe model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling JetMoeModel
  • hidden_size (int, optional, defaults to 2048) — Dimension of the hidden representations.
  • num_hidden_layers (int, optional, defaults to 12) — Number of hidden layers in the Transformer encoder.
  • num_key_value_heads (int, optional, defaults to 16) — Number of attention heads for each key and value in the Transformer encoder.
  • kv_channels (int, optional, defaults to 128) — Defines the number of channels for the key and value tensors.
  • intermediate_size (int, optional, defaults to 5632) — Dimension of the MLP representations.
  • max_position_embeddings (int, optional, defaults to 4096) — The maximum sequence length that this model might ever be used with. JetMoe’s attention allows sequence of up to 4096 tokens.
  • activation_function (string, optional, defaults to "silu") — Defines the activation function for MLP experts.
  • num_local_experts (int, optional, defaults to 8) — Defines the number of experts in the MoE and MoA.
  • num_experts_per_tok (`int, optional, defaults to 2) — The number of experts to route per-token and for MoE and MoA.
  • output_router_logits (bool, optional, defaults to False) — Whether or not the router logits should be returned by the model. Enabeling this will also allow the model to output the auxiliary loss.
  • aux_loss_coef (float, optional, defaults to 0.01) — The coefficient for the auxiliary loss.
  • 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.
  • bos_token_id (int, optional, defaults to 1) — The id of the “beginning-of-sequence” token.
  • eos_token_id (int, optional, defaults to 2) — The id of the “end-of-sequence” token.
  • tie_word_embeddings (bool, optional, defaults to True) — Whether the model’s input and output word embeddings should be tied.
  • rope_theta (float, optional, defaults to 10000.0) — The base period of the RoPE embeddings.
  • rms_norm_eps (float, optional, defaults to 1e-06) — The epsilon used by the rms normalization layers.
  • initializer_range (float, optional, defaults to 0.01) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • attention_dropout (float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities.

This is the configuration class to store the configuration of a JetMoeModel. It is used to instantiate a JetMoe model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a configuration of the JetMoe-4B.

jetmoe/jetmoe-8b

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 JetMoeModel, JetMoeConfig

>>> # Initializing a JetMoe 4B style configuration
>>> configuration = JetMoeConfig()

>>> # Initializing a model from the JetMoe 4B style configuration
>>> model = JetMoeModel(configuration)

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

JetMoeModel

class transformers.JetMoeModel

< >

( config: JetMoeConfig )

Parameters

  • config (JetMoeConfig) — 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.
  • config — JetMoeConfig

The bare JetMoe Model 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.

Transformer decoder consisting of config.num_hidden_layers layers. Each layer is a JetMoeBlock

forward

< >

( input_ids: LongTensor = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Union[transformers.cache_utils.Cache, typing.List[torch.FloatTensor], NoneType] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None output_router_logits: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None )

Parameters

  • input_ids (torch.LongTensor of shape ({0})) — Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using AutoProcenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape ({0}), 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?

  • position_ids (torch.LongTensor of shape ({0}), 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?

  • inputs_embeds (torch.FloatTensor of shape ({0}, hidden_dim), 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.
  • output_router_logits (bool, optional) — Whether or not to return the logits of all the routers. They are useful for computing the router loss, and should not be returned during inference.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • cache_position (torch.LongTensor of shape (sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.

The JetMoeModel 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.

JetMoeForCausalLM

class transformers.JetMoeForCausalLM

< >

( config )

forward

< >

( input_ids: LongTensor = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None inputs_embeds: typing.Optional[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 output_router_logits: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None cache_position: typing.Optional[torch.LongTensor] = None num_logits_to_keep: int = 0 ) → transformers.modeling_outputs.MoeCausalLMOutputWithPast or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of shape ({0})) — Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using AutoProcenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape ({0}), 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?

  • position_ids (torch.LongTensor of shape ({0}), 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?

  • inputs_embeds (torch.FloatTensor of shape ({0}, hidden_dim), 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.
  • output_router_logits (bool, optional) — Whether or not to return the logits of all the routers. They are useful for computing the router loss, and should not be returned during inference.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • cache_position (torch.LongTensor of shape (sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.
  • Args — labels (torch.LongTensor of shape (batch_size, sequence_length), optional): Labels for computing the masked language modeling loss. Indices should either be in [0, ..., config.vocab_size] or -100 (see input_ids docstring). Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].

    num_logits_to_keep (int, optional): Calculate logits for the last num_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.

Returns

transformers.modeling_outputs.MoeCausalLMOutputWithPast or tuple(torch.FloatTensor)

A transformers.modeling_outputs.MoeCausalLMOutputWithPast 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 (JetMoeConfig) 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).

  • aux_loss (torch.FloatTensor, optional, returned when labels is provided) — aux_loss for the sparse modules.

  • router_logits (tuple(torch.FloatTensor), optional, returned when output_router_probs=True and config.add_router_probs=True is passed or when config.output_router_probs=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, sequence_length, num_experts).

    Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary loss for Mixture of Experts models.

  • 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 JetMoeForCausalLM 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.

JetMoeForSequenceClassification

class transformers.JetMoeForSequenceClassification

< >

( config )

Parameters

  • config (JetMoeConfig) — 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 JetMoe Model transformer with a sequence classification head on top (linear layer).

JetMoeForSequenceClassification uses the last token in order to do the classification, as other causal models (e.g. GPT-2) do.

Since it does classification on the last token, it requires to know the position of the last token. If a pad_token_id is defined in the configuration, it finds the last token that is not a padding token in each row. If no pad_token_id is defined, it simply takes the last value in each row of the batch. Since it cannot guess the padding tokens when inputs_embeds are passed instead of input_ids, it does the same (take the last value in each row of the batch).

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.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Union[transformers.cache_utils.Cache, typing.List[torch.FloatTensor], NoneType] = None inputs_embeds: typing.Optional[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 )

Parameters

  • input_ids (torch.LongTensor of shape ({0})) — Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using AutoProcenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • attention_mask (torch.FloatTensor of shape ({0}), 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?

  • position_ids (torch.LongTensor of shape ({0}), 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?

  • inputs_embeds (torch.FloatTensor of shape ({0}, hidden_dim), 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.
  • output_router_logits (bool, optional) — Whether or not to return the logits of all the routers. They are useful for computing the router loss, and should not be returned during inference.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • cache_position (torch.LongTensor of shape (sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.
  • 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).

The JetMoeForSequenceClassification 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.

< > Update on GitHub

←Jamba Jukebox→