MPT
Overview
The MPT model was proposed by the MosaicML team and released with multiple sizes and finetuned variants. The MPT models is a series of open source and commercially usable LLMs pre-trained on 1T tokens.
MPT models are GPT-style decoder-only transformers with several improvements: performance-optimized layer implementations, architecture changes that provide greater training stability, and the elimination of context length limits by replacing positional embeddings with ALiBi.
- MPT base: MPT base pre-trained models on next token prediction
- MPT instruct: MPT base models fine-tuned on instruction based tasks
- MPT storywriter: MPT base models fine-tuned for 2500 steps on 65k-token excerpts of fiction books contained in the books3 corpus, this enables the model to handle very long sequences
The original code is available at the llm-foundry repository.
Read more about it in the release blogpost
Usage tips
- Learn more about some techniques behind training of the model in this section of llm-foundry repository
- If you want to use the advanced version of the model (triton kernels, direct flash attention integration), you can still use the original model implementation by adding
trust_remote_code=Truewhen callingfrom_pretrained.
Resources
- Fine-tuning Notebook on how to fine-tune MPT-7B on a free Google Colab instance to turn the model into a Chatbot.
MptConfig
class transformers.MptConfig
< source >( d_model: int = 2048 n_heads: int = 16 n_layers: int = 24 expansion_ratio: int = 4 max_seq_len: int = 2048 vocab_size: int = 50368 resid_pdrop: float = 0.0 layer_norm_epsilon: float = 1e-05 emb_pdrop: float = 0.0 learned_pos_emb: bool = True attn_config: MptAttentionConfig = None init_device: str = 'cpu' logit_scale: Union = None no_bias: bool = True verbose: int = 0 embedding_fraction: float = 1.0 norm_type: str = 'low_precision_layernorm' use_cache: bool = False initializer_range = 0.02 **kwargs )
Parameters
- d_model (
int, optional, defaults to 2048) — Dimensionality of the embeddings and hidden states. - n_heads (
int, optional, defaults to 16) — Number of attention heads for each attention layer in the Transformer encoder. - n_layers (
int, optional, defaults to 24) — Number of hidden layers in the Transformer encoder. - expansion_ratio (
int, optional, defaults to 4) — The ratio of the up/down scale in the MLP. - max_seq_len (
int, optional, defaults to 2048) — The maximum sequence length of the model. - vocab_size (
int, optional, defaults to 50368) — Vocabulary size of the Mpt model. Defines the maximum number of different tokens that can be represented by theinputs_idspassed when calling MptModel. Check this discussion on how thevocab_sizehas been defined. - resid_pdrop (
float, optional, defaults to 0.0) — The dropout probability applied to the attention output before combining with residual. - layer_norm_epsilon (
float, optional, defaults to 1e-05) — The epsilon to use in the layer normalization layers. - emb_pdrop (
float, optional, defaults to 0.0) — The dropout probability for the embedding layer. - learned_pos_emb (
bool, optional, defaults toTrue) — Whether to use learned positional embeddings. - attn_config (
dict, optional) — A dictionary used to configure the model’s attention module. - init_device (
str, optional, defaults to"cpu") — The device to use for parameter initialization. Defined for backward compatibility - logit_scale (
float, optional) — If not None, scale the logits by this value. - no_bias (
bool, optional, defaults toTrue) — Whether to use bias in all linear layers. - verbose (
int, optional, defaults to 0) — The verbosity level to use for logging. Used in the previous versions of MPT models for logging. This argument is deprecated. - embedding_fraction (
float, optional, defaults to 1.0) — The fraction to scale the gradients of the embedding layer by. - norm_type (
str, optional, defaults to"low_precision_layernorm") — Type of layer norm to use. All MPT models uses the same layer norm implementation. Defined for backward compatibility. - use_cache (
bool, optional, defaults toFalse) — Whether or not the model should return the last key/values attentions (not used by all models). - initializer_range (
float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
This is the configuration class to store the configuration of a MptModel. It is used to instantiate a Mpt model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to the Mpt-7b architecture mosaicml/mpt-7b.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> from transformers import MptConfig, MptModel
>>> # Initializing a Mpt configuration
>>> configuration = MptConfig()
>>> # Initializing a model (with random weights) from the configuration
>>> model = MptModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.configMptModel
class transformers.MptModel
< source >( config: MptConfig )
Parameters
- config (MptConfig) — 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 Mpt Model transformer outputting raw hidden-states without any specific head on top.
This model inherits from 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 etc.)
This model is also a PyTorch 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.
forward
< source >( input_ids: Optional = None past_key_values: Optional = None attention_mask: Optional = None inputs_embeds: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, input_ids_length)) —input_ids_length=sequence_lengthifpast_key_valuesisNoneelsepast_key_values[0][0].shape[2](sequence_lengthof input past key value states). Indices of input sequence tokens in the vocabulary.If
past_key_valuesis used, onlyinput_idsthat do not have their past calculated should be passed asinput_ids.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- past_key_values (
Tuple[Tuple[torch.Tensor]]of lengthconfig.n_layers) — Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_valuesoutput below). Can be used to speed up sequential decoding. Theinput_idswhich have their past given to this model should not be passed asinput_idsas they have already been computed.Each element of
past_key_valuesis a tuple (past_key, past_value):- past_key: [batch_size * num_heads, head_dim, kv_length]
- past_value: [batch_size * num_heads, kv_length, head_dim]
- attention_mask (
torch.FloatTensorof 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.
- inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
past_key_valuesis used, optionally only the lastinputs_embedshave to be input (seepast_key_values). - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions 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 (MptConfig) and inputs.
-
last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.If
past_key_valuesis 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 whenuse_cache=Trueis passed or whenconfig.use_cache=True) — Tuple oftuple(torch.FloatTensor)of lengthconfig.n_layers, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally ifconfig.is_encoder_decoder=True2 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=Truein the cross-attention blocks) that can be used (seepast_key_valuesinput) to speed up sequential decoding. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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 whenoutput_attentions=Trueandconfig.add_cross_attention=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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.
The MptModel 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, MptModel
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("mosaicml/mpt-7b")
>>> model = MptModel.from_pretrained("mosaicml/mpt-7b")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_stateMptForCausalLM
class transformers.MptForCausalLM
< source >( config: MptConfig )
Parameters
- config (MptConfig) — 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 MPT Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
This model inherits from 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 etc.)
This model is also a PyTorch 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.
forward
< source >( input_ids: Optional = None past_key_values: Optional = None attention_mask: Optional = None inputs_embeds: Optional = None labels: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, input_ids_length)) —input_ids_length=sequence_lengthifpast_key_valuesisNoneelsepast_key_values[0][0].shape[2](sequence_lengthof input past key value states). Indices of input sequence tokens in the vocabulary.If
past_key_valuesis used, onlyinput_idsthat do not have their past calculated should be passed asinput_ids.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- past_key_values (
Tuple[Tuple[torch.Tensor]]of lengthconfig.n_layers) — Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_valuesoutput below). Can be used to speed up sequential decoding. Theinput_idswhich have their past given to this model should not be passed asinput_idsas they have already been computed.Each element of
past_key_valuesis a tuple (past_key, past_value):- past_key: [batch_size * num_heads, head_dim, kv_length]
- past_value: [batch_size * num_heads, kv_length, head_dim]
- attention_mask (
torch.FloatTensorof 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.
- inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
past_key_valuesis used, optionally only the lastinputs_embedshave to be input (seepast_key_values). - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Labels for language modeling. Note that the labels are shifted inside the model, i.e. you can setlabels = input_idsIndices are selected in[-100, 0, ..., config.vocab_size]All labels set to-100are ignored (masked), the loss is only computed for labels in[0, ..., config.vocab_size]
Returns
transformers.modeling_outputs.CausalLMOutputWithCrossAttentions or tuple(torch.FloatTensor)
A 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 (MptConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss (for next-token prediction). -
logits (
torch.FloatTensorof 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 whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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 (
tuple(tuple(torch.FloatTensor)), optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — Tuple oftorch.FloatTensortuples of lengthconfig.n_layers, with each tuple containing the cached key, value states of the self-attention and the cross-attention layers if model is used in encoder-decoder setting. Only relevant ifconfig.is_decoder = True.Contains pre-computed hidden-states (key and values in the attention blocks) that can be used (see
past_key_valuesinput) to speed up sequential decoding.
The MptForCausalLM 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:
>>> import torch
>>> from transformers import AutoTokenizer, MptForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("mosaicml/mpt-7b")
>>> model = MptForCausalLM.from_pretrained("mosaicml/mpt-7b")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs, labels=inputs["input_ids"])
>>> loss = outputs.loss
>>> logits = outputs.logitsMptForSequenceClassification
class transformers.MptForSequenceClassification
< source >( config: MptConfig )
Parameters
- config (MptConfig) — 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 MPT Model transformer with a sequence classification head on top (linear layer).
MptForSequenceClassification uses the last token in order to do the classification, as other causal models (e.g. GPT-1) 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 inherits from 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 etc.)
This model is also a PyTorch 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.
forward
< source >( input_ids: Optional = None past_key_values: Optional = None attention_mask: Optional = None inputs_embeds: Optional = None labels: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.SequenceClassifierOutputWithPast or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, input_ids_length)) —input_ids_length=sequence_lengthifpast_key_valuesisNoneelsepast_key_values[0][0].shape[2](sequence_lengthof input past key value states). Indices of input sequence tokens in the vocabulary.If
past_key_valuesis used, onlyinput_idsthat do not have their past calculated should be passed asinput_ids.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- past_key_values (
Tuple[Tuple[torch.Tensor]]of lengthconfig.n_layers) — Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_valuesoutput below). Can be used to speed up sequential decoding. Theinput_idswhich have their past given to this model should not be passed asinput_idsas they have already been computed.Each element of
past_key_valuesis a tuple (past_key, past_value):- past_key: [batch_size * num_heads, head_dim, kv_length]
- past_value: [batch_size * num_heads, kv_length, head_dim]
- attention_mask (
torch.FloatTensorof 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.
- inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
past_key_valuesis used, optionally only the lastinputs_embedshave to be input (seepast_key_values). - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof shape(batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]. Ifconfig.num_labels == 1a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.SequenceClassifierOutputWithPast or tuple(torch.FloatTensor)
A transformers.modeling_outputs.SequenceClassifierOutputWithPast 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 (MptConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor)), optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — Tuple oftuple(torch.FloatTensor)of lengthconfig.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_valuesinput) to speed up sequential decoding. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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 MptForSequenceClassification 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 of single-label classification:
>>> import torch
>>> from transformers import AutoTokenizer, MptForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("mosaicml/mpt-7b")
>>> model = MptForSequenceClassification.from_pretrained("mosaicml/mpt-7b")
>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> with torch.no_grad():
... logits = model(**inputs).logits
>>> predicted_class_id = logits.argmax().item()
>>> # 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 = MptForSequenceClassification.from_pretrained("mosaicml/mpt-7b", num_labels=num_labels)
>>> labels = torch.tensor([1])
>>> loss = model(**inputs, labels=labels).lossExample of multi-label classification:
>>> import torch
>>> from transformers import AutoTokenizer, MptForSequenceClassification
>>> tokenizer = AutoTokenizer.from_pretrained("mosaicml/mpt-7b")
>>> model = MptForSequenceClassification.from_pretrained("mosaicml/mpt-7b", 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 = MptForSequenceClassification.from_pretrained(
... "mosaicml/mpt-7b", 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).lossMptForTokenClassification
class transformers.MptForTokenClassification
< source >( config: MptConfig )
Parameters
- config (MptConfig) — 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.
MPT Model 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. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings etc.)
This model is also a PyTorch 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.
forward
< source >( input_ids: Optional = None past_key_values: Optional = None attention_mask: Optional = None inputs_embeds: Optional = None labels: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None **deprecated_arguments ) → transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, input_ids_length)) —input_ids_length=sequence_lengthifpast_key_valuesisNoneelsepast_key_values[0][0].shape[2](sequence_lengthof input past key value states). Indices of input sequence tokens in the vocabulary.If
past_key_valuesis used, onlyinput_idsthat do not have their past calculated should be passed asinput_ids.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- past_key_values (
Tuple[Tuple[torch.Tensor]]of lengthconfig.n_layers) — Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_valuesoutput below). Can be used to speed up sequential decoding. Theinput_idswhich have their past given to this model should not be passed asinput_idsas they have already been computed.Each element of
past_key_valuesis a tuple (past_key, past_value):- past_key: [batch_size * num_heads, head_dim, kv_length]
- past_value: [batch_size * num_heads, kv_length, head_dim]
- attention_mask (
torch.FloatTensorof 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.
- inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
past_key_valuesis used, optionally only the lastinputs_embedshave to be input (seepast_key_values). - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof shape(batch_size,), optional) — Labels for computing the sequence classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]. Ifconfig.num_labels == 1a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.TokenClassifierOutput or tuple(torch.FloatTensor)
A 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 (MptConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification loss. -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.num_labels)) — Classification scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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 MptForTokenClassification 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, MptForTokenClassification
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("mosaicml/mpt-7b")
>>> model = MptForTokenClassification.from_pretrained("mosaicml/mpt-7b")
>>> 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]]
>>> labels = predicted_token_class_ids
>>> loss = model(**inputs, labels=labels).lossMptForQuestionAnswering
class transformers.MptForQuestionAnswering
< source >( config )
Parameters
- config (MptConfig) — 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 MPT Model transformer with a span classification head on top for extractive question-answering tasks like SQuAD
(a linear layers on top of the hidden-states output to compute span start logits and span end logits).
This model inherits from 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 etc.)
This model is also a PyTorch 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.
forward
< source >( input_ids: Optional = None attention_mask: Optional = None inputs_embeds: Optional = None start_positions: Optional = None end_positions: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None )
Parameters
- input_ids (
torch.LongTensorof shape(batch_size, input_ids_length)) —input_ids_length=sequence_lengthifpast_key_valuesisNoneelsepast_key_values[0][0].shape[2](sequence_lengthof input past key value states). Indices of input sequence tokens in the vocabulary.If
past_key_valuesis used, onlyinput_idsthat do not have their past calculated should be passed asinput_ids.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- past_key_values (
Tuple[Tuple[torch.Tensor]]of lengthconfig.n_layers) — Contains precomputed hidden-states (key and values in the attention blocks) as computed by the model (seepast_key_valuesoutput below). Can be used to speed up sequential decoding. Theinput_idswhich have their past given to this model should not be passed asinput_idsas they have already been computed.Each element of
past_key_valuesis a tuple (past_key, past_value):- past_key: [batch_size * num_heads, head_dim, kv_length]
- past_value: [batch_size * num_heads, kv_length, head_dim]
- attention_mask (
torch.FloatTensorof 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.
- inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix.If
past_key_valuesis used, optionally only the lastinputs_embedshave to be input (seepast_key_values). - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - start_positions (
torch.LongTensorof 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.LongTensorof 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.
The MptForQuestionAnswering 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.