Tokenizers
models
Definitions of all models available in Transformers.js.
Example: Load and run an AutoModel
.
Copied
import { AutoModel, AutoTokenizer } from '@xenova/transformers';
let tokenizer = await AutoTokenizer.from_pretrained('Xenova/bert-base-uncased');
let model = await AutoModel.from_pretrained('Xenova/bert-base-uncased');
let inputs = await tokenizer('I love transformers!');
let { logits } = await model(inputs);
// Tensor {
// data: Float32Array(183132) [-7.117443084716797, -7.107812881469727, -7.092104911804199, ...]
// dims: (3) [1, 6, 30522],
// type: "float32",
// size: 183132,
// }
We also provide other AutoModel
s (listed below), which you can use in the same way as the Python library. For example:
Example: Load and run a AutoModelForSeq2SeqLM
.
Copied
import { AutoModelForSeq2SeqLM, AutoTokenizer } from '@xenova/transformers';
let tokenizer = await AutoTokenizer.from_pretrained('Xenova/t5-small');
let model = await AutoModelForSeq2SeqLM.from_pretrained('Xenova/t5-small');
let { input_ids } = await tokenizer('translate English to German: I love transformers!');
let outputs = await model.generate(input_ids);
let decoded = tokenizer.decode(outputs[0], { skip_special_tokens: true });
// 'Ich liebe Transformatoren!'
static
instance
.dispose()
⇒Promise.<Array<unknown>>
._call(model_inputs)
⇒Promise.<Object>
.forward(model_inputs)
⇒Promise.<Object>
._get_generation_config(generation_config)
⇒GenerationConfig
.groupBeams(beams)
⇒Array
.getAttentions(decoderResults)
⇒Object
static
.from_pretrained(pretrained_model_name_or_path, options)
⇒Promise.<PreTrainedModel>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
.BertForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
.CamembertForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
.CamembertForTokenClassification
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
.CamembertForQuestionAnswering
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
.DebertaForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
.DebertaForTokenClassification
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
.DebertaV2ForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
.DebertaV2ForTokenClassification
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
.DebertaV2ForQuestionAnswering
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
.DistilBertForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
.DistilBertForTokenClassification
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
.DistilBertForQuestionAnswering
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
.MobileBertForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
.MobileBertForQuestionAnswering
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
.MPNetForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
.BartForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
.MBartForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
.RobertaForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
.RobertaForTokenClassification
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
._call(model_inputs)
⇒Promise.<MaskedLMOutput>
.XLMRobertaForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
.XLMRobertaForTokenClassification
._call(model_inputs)
⇒Promise.<TokenClassifierOutput>
.XLMRobertaForQuestionAnswering
._call(model_inputs)
⇒Promise.<QuestionAnsweringModelOutput>
.from_pretrained()
:PreTrainedModel.from_pretrained
.CLIPVisionModelWithProjection
.from_pretrained()
:PreTrainedModel.from_pretrained
.WavLMForSequenceClassification
._call(model_inputs)
⇒Promise.<SequenceClassifierOutput>
instance
static
.from_pretrained()
:PreTrainedModel.from_pretrained
inner
~TypedArray
:*
~DecoderOutput
⇒Promise.<(Array<Array<number>>|EncoderDecoderOutput|DecoderOutput)>
~WhisperGenerationConfig
:Object
~SpeechOutput
:Object
models.PreTrainedModel
A base class for pre-trained models that provides the model configuration and an ONNX session.
Kind: static class of models
instance
.dispose()
⇒Promise.<Array<unknown>>
._call(model_inputs)
⇒Promise.<Object>
.forward(model_inputs)
⇒Promise.<Object>
._get_generation_config(generation_config)
⇒GenerationConfig
.groupBeams(beams)
⇒Array
.getAttentions(decoderResults)
⇒Object
static
.from_pretrained(pretrained_model_name_or_path, options)
⇒Promise.<PreTrainedModel>
new PreTrainedModel(config, session)
Creates a new instance of the PreTrainedModel
class.
config
Object
The model configuration.
session
any
session for the model.
preTrainedModel.dispose() ⇒ <code> Promise. < Array < unknown > > </code>
Disposes of all the ONNX sessions that were created during inference.
Kind: instance method of PreTrainedModel
Returns: Promise.<Array<unknown>>
- An array of promises, one for each ONNX session that is being disposed.
Todo
preTrainedModel._call(model_inputs) ⇒ <code> Promise. < Object > </code>
Runs the model with the provided inputs
Kind: instance method of PreTrainedModel
Returns: Promise.<Object>
- Object containing output tensors
model_inputs
Object
Object containing input tensors
preTrainedModel.forward(model_inputs) ⇒ <code> Promise. < Object > </code>
Forward method for a pretrained model. If not overridden by a subclass, the correct forward method will be chosen based on the model type.
Kind: instance method of PreTrainedModel
Returns: Promise.<Object>
- The output data from the model in the format specified in the ONNX model.
Throws:
Error
This method must be implemented in subclasses.
model_inputs
Object
The input data to the model in the format specified in the ONNX model.
preTrainedModel._get_generation_config(generation_config) ⇒ <code> GenerationConfig </code>
This function merges multiple generation configs together to form a final generation config to be used by the model for text generation. It first creates an empty GenerationConfig
object, then it applies the model’s own generation_config
property to it. Finally, if a generation_config
object was passed in the arguments, it overwrites the corresponding properties in the final config with those of the passed config object.
Kind: instance method of PreTrainedModel
Returns: GenerationConfig
- The final generation config object to be used by the model for text generation.
generation_config
GenerationConfig
A GenerationConfig
object containing generation parameters.
preTrainedModel.groupBeams(beams) ⇒ <code> Array </code>
Groups an array of beam objects by their ids.
Kind: instance method of PreTrainedModel
Returns: Array
- An array of arrays, where each inner array contains beam objects with the same id.
beams
Array
The array of beam objects to group.
preTrainedModel.getPastKeyValues(decoderResults, pastKeyValues) ⇒ <code> Object </code>
Returns an object containing past key values from the given decoder results object.
Kind: instance method of PreTrainedModel
Returns: Object
- An object containing past key values.
decoderResults
Object
The decoder results object.
pastKeyValues
Object
The previous past key values.
preTrainedModel.getAttentions(decoderResults) ⇒ <code> Object </code>
Returns an object containing attentions from the given decoder results object.
Kind: instance method of PreTrainedModel
Returns: Object
- An object containing attentions.
decoderResults
Object
The decoder results object.
preTrainedModel.addPastKeyValues(decoderFeeds, pastKeyValues)
Adds past key values to the decoder feeds object. If pastKeyValues is null, creates new tensors for past key values.
Kind: instance method of PreTrainedModel
decoderFeeds
Object
The decoder feeds object to add past key values to.
pastKeyValues
Object
An object containing past key values.
PreTrainedModel.from_pretrained(pretrained_model_name_or_path, options) ⇒ <code> Promise. < PreTrainedModel > </code>
Instantiate one of the model classes of the library from a pretrained model.
The model class to instantiate is selected based on the model_type
property of the config object (either passed as an argument or loaded from pretrained_model_name_or_path
if possible)
Kind: static method of PreTrainedModel
Returns: Promise.<PreTrainedModel>
- A new instance of the PreTrainedModel
class.
pretrained_model_name_or_path
string
The name or path of the pretrained model. Can be either:
A string, the model id of a pretrained model hosted inside a model repo on boincai.com. Valid model ids can be located at the root-level, like
bert-base-uncased
, or namespaced under a user or organization name, likedbmdz/bert-base-german-cased
.A path to a directory containing model weights, e.g.,
./my_model_directory/
.
options
*
Additional options for loading the model.
models.BaseModelOutput
Base class for model’s outputs, with potential hidden states and attentions.
Kind: static class of models
new BaseModelOutput(output)
output
Object
The output of the model.
output.last_hidden_state
Tensor
Sequence of hidden-states at the output of the last layer of the model.
[output.hidden_states]
Tensor
Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
[output.attentions]
Tensor
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
models.BertForMaskedLM
BertForMaskedLM is a class representing a BERT model for masked language modeling.
Kind: static class of models
bertForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of BertForMaskedLM
Returns: Promise.<MaskedLMOutput>
- An object containing the model’s output logits for masked language modeling.
model_inputs
Object
The inputs to the model.
models.BertForSequenceClassification
BertForSequenceClassification is a class representing a BERT model for sequence classification.
Kind: static class of models
bertForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of BertForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.BertForTokenClassification
BertForTokenClassification is a class representing a BERT model for token classification.
Kind: static class of models
bertForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of BertForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.BertForQuestionAnswering
BertForQuestionAnswering is a class representing a BERT model for question answering.
Kind: static class of models
bertForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of BertForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- An object containing the model’s output logits for question answering.
model_inputs
Object
The inputs to the model.
models.CamembertModel
The bare CamemBERT Model transformer outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.CamembertForMaskedLM
CamemBERT Model with a language modeling
head on top.
Kind: static class of models
camembertForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of CamembertForMaskedLM
Returns: Promise.<MaskedLMOutput>
- An object containing the model’s output logits for masked language modeling.
model_inputs
Object
The inputs to the model.
models.CamembertForSequenceClassification
CamemBERT Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output) e.g. for GLUE tasks.
Kind: static class of models
camembertForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of CamembertForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.CamembertForTokenClassification
CamemBERT 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.
Kind: static class of models
camembertForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of CamembertForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.CamembertForQuestionAnswering
CamemBERT Model with a span classification head on top for extractive question-answering tasks
Kind: static class of models
camembertForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of CamembertForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- An object containing the model’s output logits for question answering.
model_inputs
Object
The inputs to the model.
models.DebertaModel
The bare DeBERTa Model transformer outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.DebertaForMaskedLM
DeBERTa Model with a language modeling
head on top.
Kind: static class of models
debertaForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of DebertaForMaskedLM
Returns: Promise.<MaskedLMOutput>
- An object containing the model’s output logits for masked language modeling.
model_inputs
Object
The inputs to the model.
models.DebertaForSequenceClassification
DeBERTa Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output)
Kind: static class of models
debertaForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of DebertaForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.DebertaForTokenClassification
DeBERTa 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.
Kind: static class of models
debertaForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of DebertaForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.DebertaForQuestionAnswering
DeBERTa Model 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
).
Kind: static class of models
debertaForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of DebertaForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- An object containing the model’s output logits for question answering.
model_inputs
Object
The inputs to the model.
models.DebertaV2Model
The bare DeBERTa-V2 Model transformer outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.DebertaV2ForMaskedLM
DeBERTa-V2 Model with a language modeling
head on top.
Kind: static class of models
debertaV2ForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of DebertaV2ForMaskedLM
Returns: Promise.<MaskedLMOutput>
- An object containing the model’s output logits for masked language modeling.
model_inputs
Object
The inputs to the model.
models.DebertaV2ForSequenceClassification
DeBERTa-V2 Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output)
Kind: static class of models
debertaV2ForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of DebertaV2ForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.DebertaV2ForTokenClassification
DeBERTa-V2 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.
Kind: static class of models
debertaV2ForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of DebertaV2ForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.DebertaV2ForQuestionAnswering
DeBERTa-V2 Model 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
).
Kind: static class of models
debertaV2ForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of DebertaV2ForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- An object containing the model’s output logits for question answering.
model_inputs
Object
The inputs to the model.
models.DistilBertForSequenceClassification
DistilBertForSequenceClassification is a class representing a DistilBERT model for sequence classification.
Kind: static class of models
distilBertForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of DistilBertForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.DistilBertForTokenClassification
DistilBertForTokenClassification is a class representing a DistilBERT model for token classification.
Kind: static class of models
distilBertForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of DistilBertForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.DistilBertForQuestionAnswering
DistilBertForQuestionAnswering is a class representing a DistilBERT model for question answering.
Kind: static class of models
distilBertForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of DistilBertForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- An object containing the model’s output logits for question answering.
model_inputs
Object
The inputs to the model.
models.DistilBertForMaskedLM
DistilBertForMaskedLM is a class representing a DistilBERT model for masking task.
Kind: static class of models
distilBertForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of DistilBertForMaskedLM
Returns: Promise.<MaskedLMOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.MobileBertForMaskedLM
MobileBertForMaskedLM is a class representing a MobileBERT model for masking task.
Kind: static class of models
mobileBertForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of MobileBertForMaskedLM
Returns: Promise.<MaskedLMOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.MobileBertForSequenceClassification
MobileBert Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled output)
Kind: static class of models
mobileBertForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of MobileBertForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.MobileBertForQuestionAnswering
MobileBert Model with a span classification head on top for extractive question-answering tasks
Kind: static class of models
mobileBertForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of MobileBertForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.MPNetModel
The bare MPNet Model transformer outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.MPNetForMaskedLM
MPNetForMaskedLM is a class representing a MPNet model for masked language modeling.
Kind: static class of models
mpNetForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of MPNetForMaskedLM
Returns: Promise.<MaskedLMOutput>
- An object containing the model’s output logits for masked language modeling.
model_inputs
Object
The inputs to the model.
models.MPNetForSequenceClassification
MPNetForSequenceClassification is a class representing a MPNet model for sequence classification.
Kind: static class of models
mpNetForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of MPNetForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.MPNetForTokenClassification
MPNetForTokenClassification is a class representing a MPNet model for token classification.
Kind: static class of models
mpNetForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of MPNetForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.MPNetForQuestionAnswering
MPNetForQuestionAnswering is a class representing a MPNet model for question answering.
Kind: static class of models
mpNetForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of MPNetForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- An object containing the model’s output logits for question answering.
model_inputs
Object
The inputs to the model.
models.T5ForConditionalGeneration
T5Model is a class representing a T5 model for conditional generation.
Kind: static class of models
new T5ForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the T5ForConditionalGeneration
class.
config
Object
The model configuration.
session
any
session for the model.
decoder_merged_session
any
session for the decoder.
generation_config
GenerationConfig
The generation configuration.
models.LongT5PreTrainedModel
An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.
Kind: static class of models
models.LongT5Model
The bare LONGT5 Model transformer outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.LongT5ForConditionalGeneration
LONGT5 Model with a language modeling
head on top.
Kind: static class of models
new LongT5ForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the LongT5ForConditionalGeneration
class.
config
Object
The model configuration.
session
any
session for the model.
decoder_merged_session
any
session for the decoder.
generation_config
GenerationConfig
The generation configuration.
models.MT5ForConditionalGeneration
A class representing a conditional sequence-to-sequence model based on the MT5 architecture.
Kind: static class of models
new MT5ForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the MT5ForConditionalGeneration
class.
config
any
The model configuration.
session
any
The ONNX session containing the encoder weights.
decoder_merged_session
any
The ONNX session containing the merged decoder weights.
generation_config
GenerationConfig
The generation configuration.
models.BartModel
The bare BART Model outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.BartForConditionalGeneration
The BART Model with a language modeling head. Can be used for summarization.
Kind: static class of models
new BartForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the BartForConditionalGeneration
class.
config
Object
The configuration object for the Bart model.
session
Object
The ONNX session used to execute the model.
decoder_merged_session
Object
The ONNX session used to execute the decoder.
generation_config
Object
The generation configuration object.
models.BartForSequenceClassification
Bart model with a sequence classification/head on top (a linear layer on top of the pooled output)
Kind: static class of models
bartForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of BartForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.MBartModel
The bare MBART Model outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.MBartForConditionalGeneration
The MBART Model with a language modeling head. Can be used for summarization, after fine-tuning the pretrained models.
Kind: static class of models
new MBartForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the MBartForConditionalGeneration
class.
config
Object
The configuration object for the Bart model.
session
Object
The ONNX session used to execute the model.
decoder_merged_session
Object
The ONNX session used to execute the decoder.
generation_config
Object
The generation configuration object.
models.MBartForSequenceClassification
MBart model with a sequence classification/head on top (a linear layer on top of the pooled output).
Kind: static class of models
mBartForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of MBartForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.MBartForCausalLM
Kind: static class of models
new MBartForCausalLM(config, decoder_merged_session, generation_config)
Creates a new instance of the MBartForCausalLM
class.
config
Object
Configuration object for the model.
decoder_merged_session
Object
ONNX Session object for the decoder.
generation_config
Object
Configuration object for the generation process.
models.BlenderbotModel
The bare Blenderbot Model outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.BlenderbotForConditionalGeneration
The Blenderbot Model with a language modeling head. Can be used for summarization.
Kind: static class of models
new BlenderbotForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the BlenderbotForConditionalGeneration
class.
config
any
The model configuration.
session
any
The ONNX session containing the encoder weights.
decoder_merged_session
any
The ONNX session containing the merged decoder weights.
generation_config
GenerationConfig
The generation configuration.
models.BlenderbotSmallModel
The bare BlenderbotSmall Model outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.BlenderbotSmallForConditionalGeneration
The BlenderbotSmall Model with a language modeling head. Can be used for summarization.
Kind: static class of models
new BlenderbotSmallForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the BlenderbotForConditionalGeneration
class.
config
any
The model configuration.
session
any
The ONNX session containing the encoder weights.
decoder_merged_session
any
The ONNX session containing the merged decoder weights.
generation_config
GenerationConfig
The generation configuration.
models.RobertaForMaskedLM
RobertaForMaskedLM class for performing masked language modeling on Roberta models.
Kind: static class of models
robertaForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of RobertaForMaskedLM
Returns: Promise.<MaskedLMOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.RobertaForSequenceClassification
RobertaForSequenceClassification class for performing sequence classification on Roberta models.
Kind: static class of models
robertaForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of RobertaForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.RobertaForTokenClassification
RobertaForTokenClassification class for performing token classification on Roberta models.
Kind: static class of models
robertaForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of RobertaForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.RobertaForQuestionAnswering
RobertaForQuestionAnswering class for performing question answering on Roberta models.
Kind: static class of models
robertaForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of RobertaForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.XLMPreTrainedModel
An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.
Kind: static class of models
models.XLMModel
The bare XLM Model transformer outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.XLMWithLMHeadModel
The XLM Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
Kind: static class of models
xlmWithLMHeadModel._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of XLMWithLMHeadModel
Returns: Promise.<MaskedLMOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.XLMForSequenceClassification
XLM Model with a sequence classification/regression head on top (a linear layer on top of the pooled output)
Kind: static class of models
xlmForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of XLMForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.XLMForTokenClassification
XLM Model with a token classification head on top (a linear layer on top of the hidden-states output)
Kind: static class of models
xlmForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of XLMForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.XLMForQuestionAnswering
XLM Model with a span classification head on top for extractive question-answering tasks
Kind: static class of models
xlmForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of XLMForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.XLMRobertaForMaskedLM
XLMRobertaForMaskedLM class for performing masked language modeling on XLMRoberta models.
Kind: static class of models
xlmRobertaForMaskedLM._call(model_inputs) ⇒ <code> Promise. < MaskedLMOutput > </code>
Calls the model on new inputs.
Kind: instance method of XLMRobertaForMaskedLM
Returns: Promise.<MaskedLMOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.XLMRobertaForSequenceClassification
XLMRobertaForSequenceClassification class for performing sequence classification on XLMRoberta models.
Kind: static class of models
xlmRobertaForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of XLMRobertaForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.XLMRobertaForTokenClassification
XLMRobertaForTokenClassification class for performing token classification on XLMRoberta models.
Kind: static class of models
xlmRobertaForTokenClassification._call(model_inputs) ⇒ <code> Promise. < TokenClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of XLMRobertaForTokenClassification
Returns: Promise.<TokenClassifierOutput>
- An object containing the model’s output logits for token classification.
model_inputs
Object
The inputs to the model.
models.XLMRobertaForQuestionAnswering
XLMRobertaForQuestionAnswering class for performing question answering on XLMRoberta models.
Kind: static class of models
xlmRobertaForQuestionAnswering._call(model_inputs) ⇒ <code> Promise. < QuestionAnsweringModelOutput > </code>
Calls the model on new inputs.
Kind: instance method of XLMRobertaForQuestionAnswering
Returns: Promise.<QuestionAnsweringModelOutput>
- returned object
model_inputs
Object
The inputs to the model.
models.WhisperModel
WhisperModel class for training Whisper models without a language model head.
Kind: static class of models
models.WhisperForConditionalGeneration
WhisperForConditionalGeneration class for generating conditional outputs from Whisper models.
Kind: static class of models
new WhisperForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the WhisperForConditionalGeneration
class.
config
Object
Configuration object for the model.
session
Object
ONNX Session object for the model.
decoder_merged_session
Object
ONNX Session object for the decoder.
generation_config
Object
Configuration object for the generation process.
whisperForConditionalGeneration.generate(inputs, generation_config, logits_processor) ⇒ <code> Promise. < Object > </code>
Generates outputs based on input and generation configuration.
Kind: instance method of WhisperForConditionalGeneration
Returns: Promise.<Object>
- Promise object represents the generated outputs.
inputs
Object
Input data for the model.
generation_config
WhisperGenerationConfig
Configuration object for the generation process.
logits_processor
Object
Optional logits processor object.
whisperForConditionalGeneration._extract_token_timestamps(generate_outputs, alignment_heads, [num_frames], [time_precision]) ⇒ <code> Tensor </code>
Calculates token-level timestamps using the encoder-decoder cross-attentions and dynamic time-warping (DTW) to map each output token to a position in the input audio.
Kind: instance method of WhisperForConditionalGeneration
Returns: Tensor
- tensor containing the timestamps in seconds for each predicted token
generate_outputs
Object
Outputs generated by the model
generate_outputs.cross_attentions
Array.<Array<Array<Tensor>>>
The cross attentions output by the model
generate_outputs.decoder_attentions
Array.<Array<Array<Tensor>>>
The decoder attentions output by the model
generate_outputs.sequences
Array.<Array<number>>
The sequences output by the model
alignment_heads
Array.<Array<number>>
Alignment heads of the model
[num_frames]
number
Number of frames in the input audio.
[time_precision]
number
0.02
Precision of the timestamps in seconds
models.VisionEncoderDecoderModel
Vision Encoder-Decoder model based on OpenAI’s GPT architecture for image captioning and other vision tasks
Kind: static class of models
new VisionEncoderDecoderModel(config, session, decoder_merged_session, generation_config)
Creates a new instance of the VisionEncoderDecoderModel
class.
config
Object
The configuration object specifying the hyperparameters and other model settings.
session
Object
The ONNX session containing the encoder model.
decoder_merged_session
any
The ONNX session containing the merged decoder model.
generation_config
Object
Configuration object for the generation process.
models.CLIPModel
CLIP Text and Vision Model with a projection layers on top
Example: Perform zero-shot image classification with a CLIPModel
.
Copied
import { AutoTokenizer, AutoProcessor, CLIPModel, RawImage } from '@xenova/transformers';
// Load tokenizer, processor, and model
let tokenizer = await AutoTokenizer.from_pretrained('Xenova/clip-vit-base-patch16');
let processor = await AutoProcessor.from_pretrained('Xenova/clip-vit-base-patch16');
let model = await CLIPModel.from_pretrained('Xenova/clip-vit-base-patch16');
// Run tokenization
let texts = ['a photo of a car', 'a photo of a football match']
let text_inputs = tokenizer(texts, { padding: true, truncation: true });
// Read image and run processor
let image = await RawImage.read('https://boincai.com/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg');
let image_inputs = await processor(image);
// Run model with both text and pixel inputs
let output = await model({ ...text_inputs, ...image_inputs });
// {
// logits_per_image: Tensor {
// dims: [ 1, 2 ],
// data: Float32Array(2) [ 18.579734802246094, 24.31830596923828 ],
// },
// logits_per_text: Tensor {
// dims: [ 2, 1 ],
// data: Float32Array(2) [ 18.579734802246094, 24.31830596923828 ],
// },
// text_embeds: Tensor {
// dims: [ 2, 512 ],
// data: Float32Array(1024) [ ... ],
// },
// image_embeds: Tensor {
// dims: [ 1, 512 ],
// data: Float32Array(512) [ ... ],
// }
// }
Kind: static class of models
models.CLIPTextModelWithProjection
CLIP Text Model with a projection layer on top (a linear layer on top of the pooled output)
Example: Compute text embeddings with CLIPTextModelWithProjection
.
Copied
import { AutoTokenizer, CLIPTextModelWithProjection } from '@xenova/transformers';
// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained('Xenova/clip-vit-base-patch16');
const text_model = await CLIPTextModelWithProjection.from_pretrained('Xenova/clip-vit-base-patch16');
// Run tokenization
let texts = ['a photo of a car', 'a photo of a football match'];
let text_inputs = tokenizer(texts, { padding: true, truncation: true });
// Compute embeddings
const { text_embeds } = await text_model(text_inputs);
// Tensor {
// dims: [ 2, 512 ],
// type: 'float32',
// data: Float32Array(1024) [ ... ],
// size: 1024
// }
Kind: static class of models
CLIPTextModelWithProjection.from_pretrained() : <code> PreTrainedModel.from_pretrained </code>
Kind: static method of CLIPTextModelWithProjection
models.CLIPVisionModelWithProjection
CLIP Vision Model with a projection layer on top (a linear layer on top of the pooled output)
Example: Compute vision embeddings with CLIPVisionModelWithProjection
.
Copied
import { AutoProcessor, CLIPVisionModelWithProjection, RawImage} from '@xenova/transformers';
// Load processor and vision model
const processor = await AutoProcessor.from_pretrained('Xenova/clip-vit-base-patch16');
const vision_model = await CLIPVisionModelWithProjection.from_pretrained('Xenova/clip-vit-base-patch16');
// Read image and run processor
let image = await RawImage.read('https://boincai.com/datasets/Xenova/transformers.js-docs/resolve/main/football-match.jpg');
let image_inputs = await processor(image);
// Compute embeddings
const { image_embeds } = await vision_model(image_inputs);
// Tensor {
// dims: [ 1, 512 ],
// type: 'float32',
// data: Float32Array(512) [ ... ],
// size: 512
// }
Kind: static class of models
CLIPVisionModelWithProjection.from_pretrained() : <code> PreTrainedModel.from_pretrained </code>
Kind: static method of CLIPVisionModelWithProjection
models.GPT2PreTrainedModel
Kind: static class of models
new GPT2PreTrainedModel(config, session, generation_config)
Creates a new instance of the GPT2PreTrainedModel
class.
config
Object
The configuration of the model.
session
any
The ONNX session containing the model weights.
generation_config
GenerationConfig
The generation configuration.
models.GPT2LMHeadModel
GPT-2 language model head on top of the GPT-2 base model. This model is suitable for text generation tasks.
Kind: static class of models
models.GPTNeoPreTrainedModel
Kind: static class of models
new GPTNeoPreTrainedModel(config, session, generation_config)
Creates a new instance of the GPTNeoPreTrainedModel
class.
config
Object
The configuration of the model.
session
any
The ONNX session containing the model weights.
generation_config
GenerationConfig
The generation configuration.
models.GPTNeoXPreTrainedModel
Kind: static class of models
new GPTNeoXPreTrainedModel(config, session, generation_config)
Creates a new instance of the GPTNeoXPreTrainedModel
class.
config
Object
The configuration of the model.
session
any
The ONNX session containing the model weights.
generation_config
GenerationConfig
The generation configuration.
models.GPTJPreTrainedModel
Kind: static class of models
new GPTJPreTrainedModel(config, session, generation_config)
Creates a new instance of the GPTJPreTrainedModel
class.
config
Object
The configuration of the model.
session
any
The ONNX session containing the model weights.
generation_config
GenerationConfig
The generation configuration.
models.GPTBigCodePreTrainedModel
Kind: static class of models
new GPTBigCodePreTrainedModel(config, session, generation_config)
Creates a new instance of the GPTBigCodePreTrainedModel
class.
config
Object
The configuration of the model.
session
any
The ONNX session containing the model weights.
generation_config
GenerationConfig
The generation configuration.
models.CodeGenPreTrainedModel
Kind: static class of models
new CodeGenPreTrainedModel(config, session, generation_config)
Creates a new instance of the CodeGenPreTrainedModel
class.
config
Object
The model configuration object.
session
Object
The ONNX session object.
generation_config
GenerationConfig
The generation configuration.
models.CodeGenModel
CodeGenModel is a class representing a code generation model without a language model head.
Kind: static class of models
models.CodeGenForCausalLM
CodeGenForCausalLM is a class that represents a code generation model based on the GPT-2 architecture. It extends the CodeGenPreTrainedModel
class.
Kind: static class of models
models.LlamaPreTrainedModel
The bare LLama Model outputting raw hidden-states without any specific head on top.
Kind: static class of models
new LlamaPreTrainedModel(config, session, generation_config)
Creates a new instance of the LlamaPreTrainedModel
class.
config
Object
The model configuration object.
session
Object
The ONNX session object.
generation_config
GenerationConfig
The generation configuration.
models.LlamaModel
The bare LLaMA Model outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.BloomPreTrainedModel
The Bloom Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
Kind: static class of models
new BloomPreTrainedModel(config, session, generation_config)
Creates a new instance of the BloomPreTrainedModel
class.
config
Object
The configuration of the model.
session
any
The ONNX session containing the model weights.
generation_config
GenerationConfig
The generation configuration.
models.BloomModel
The bare Bloom Model transformer outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.BloomForCausalLM
The Bloom Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
Kind: static class of models
models.MptPreTrainedModel
Kind: static class of models
new MptPreTrainedModel(config, session, generation_config)
Creates a new instance of the MptPreTrainedModel
class.
config
Object
The model configuration object.
session
Object
The ONNX session object.
generation_config
GenerationConfig
The generation configuration.
models.MptModel
The bare Mpt Model transformer outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.MptForCausalLM
The MPT Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
Kind: static class of models
models.OPTPreTrainedModel
Kind: static class of models
new OPTPreTrainedModel(config, session, generation_config)
Creates a new instance of the OPTPreTrainedModel
class.
config
Object
The model configuration object.
session
Object
The ONNX session object.
generation_config
GenerationConfig
The generation configuration.
models.OPTModel
The bare OPT Model outputting raw hidden-states without any specific head on top.
Kind: static class of models
models.OPTForCausalLM
The OPT Model transformer with a language modeling head on top (linear layer with weights tied to the input embeddings).
Kind: static class of models
models.DetrObjectDetectionOutput
Kind: static class of models
new DetrObjectDetectionOutput(output)
output
Object
The output of the model.
output.logits
Tensor
Classification logits (including no-object) for all queries.
output.pred_boxes
Tensor
Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These values are normalized in [0, 1], relative to the size of each individual image in the batch (disregarding possible padding).
models.DetrSegmentationOutput
Kind: static class of models
new DetrSegmentationOutput(output)
output
Object
The output of the model.
output.logits
Tensor
The output logits of the model.
output.pred_boxes
Tensor
Predicted boxes.
output.pred_masks
Tensor
Predicted masks.
models.ResNetPreTrainedModel
An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.
Kind: static class of models
models.ResNetModel
The bare ResNet model outputting raw features without any specific head on top.
Kind: static class of models
models.ResNetForImageClassification
ResNet Model with an image classification head on top (a linear layer on top of the pooled features), e.g. for ImageNet.
Kind: static class of models
resNetForImageClassification._call(model_inputs)
Kind: instance method of ResNetForImageClassification
model_inputs
any
models.DonutSwinModel
The bare Donut Swin Model transformer outputting raw hidden-states without any specific head on top.
Example: Step-by-step Document Parsing.
Copied
import { AutoProcessor, AutoTokenizer, AutoModelForVision2Seq, RawImage } from '@xenova/transformers';
// Choose model to use
const model_id = 'Xenova/donut-base-finetuned-cord-v2';
// Prepare image inputs
const processor = await AutoProcessor.from_pretrained(model_id);
const url = 'https://boincai.com/datasets/Xenova/transformers.js-docs/resolve/main/receipt.png';
const image = await RawImage.read(url);
const image_inputs = await processor(image);
// Prepare decoder inputs
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const task_prompt = '<s_cord-v2>';
const decoder_input_ids = tokenizer(task_prompt, {
add_special_tokens: false,
}).input_ids;
// Create the model
const model = await AutoModelForVision2Seq.from_pretrained(model_id);
// Run inference
const output = await model.generate(image_inputs.pixel_values, {
decoder_input_ids,
max_length: model.config.decoder.max_position_embeddings,
});
// Decode output
const decoded = tokenizer.batch_decode(output)[0];
// <s_cord-v2><s_menu><s_nm> CINNAMON SUGAR</s_nm><s_unitprice> 17,000</s_unitprice><s_cnt> 1 x</s_cnt><s_price> 17,000</s_price></s_menu><s_sub_total><s_subtotal_price> 17,000</s_subtotal_price></s_sub_total><s_total><s_total_price> 17,000</s_total_price><s_cashprice> 20,000</s_cashprice><s_changeprice> 3,000</s_changeprice></s_total></s>
Example: Step-by-step Document Visual Question Answering (DocVQA)
Copied
import { AutoProcessor, AutoTokenizer, AutoModelForVision2Seq, RawImage } from '@xenova/transformers';
// Choose model to use
const model_id = 'Xenova/donut-base-finetuned-docvqa';
// Prepare image inputs
const processor = await AutoProcessor.from_pretrained(model_id);
const url = 'https://boincai.com/datasets/Xenova/transformers.js-docs/resolve/main/invoice.png';
const image = await RawImage.read(url);
const image_inputs = await processor(image);
// Prepare decoder inputs
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const question = 'What is the invoice number?';
const task_prompt = `<s_docvqa><s_question>${question}</s_question><s_answer>`;
const decoder_input_ids = tokenizer(task_prompt, {
add_special_tokens: false,
}).input_ids;
// Create the model
const model = await AutoModelForVision2Seq.from_pretrained(model_id);
// Run inference
const output = await model.generate(image_inputs.pixel_values, {
decoder_input_ids,
max_length: model.config.decoder.max_position_embeddings,
});
// Decode output
const decoded = tokenizer.batch_decode(output)[0];
// <s_docvqa><s_question> What is the invoice number?</s_question><s_answer> us-001</s_answer></s>
Kind: static class of models
models.YolosObjectDetectionOutput
Kind: static class of models
new YolosObjectDetectionOutput(output)
output
Object
The output of the model.
output.logits
Tensor
Classification logits (including no-object) for all queries.
output.pred_boxes
Tensor
Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These values are normalized in [0, 1], relative to the size of each individual image in the batch (disregarding possible padding).
models.SamImageSegmentationOutput
Base class for Segment-Anything model’s output.
Kind: static class of models
new SamImageSegmentationOutput(output)
output
Object
The output of the model.
output.iou_scores
Tensor
The output logits of the model.
output.pred_masks
Tensor
Predicted boxes.
models.MarianMTModel
Kind: static class of models
new MarianMTModel(config, session, decoder_merged_session, generation_config)
Creates a new instance of the MarianMTModel
class.
config
Object
The model configuration object.
session
Object
The ONNX session object.
decoder_merged_session
any
generation_config
any
models.M2M100ForConditionalGeneration
Kind: static class of models
new M2M100ForConditionalGeneration(config, session, decoder_merged_session, generation_config)
Creates a new instance of the M2M100ForConditionalGeneration
class.
config
Object
The model configuration object.
session
Object
The ONNX session object.
decoder_merged_session
any
generation_config
any
models.Wav2Vec2Model
The bare Wav2Vec2 Model transformer outputting raw hidden-states without any specific head on top.
Example: Load and run an Wav2Vec2Model
for feature extraction.
Copied
import { AutoProcessor, AutoModel, read_audio } from '@xenova/transformers';
// Read and preprocess audio
const processor = await AutoProcessor.from_pretrained('Xenova/mms-300m');
const audio = await read_audio('https://boincai.com/datasets/Narsil/asr_dummy/resolve/main/mlk.flac', 16000);
const inputs = await processor(audio);
// Run model with inputs
const model = await AutoModel.from_pretrained('Xenova/mms-300m');
const output = await model(inputs);
// {
// last_hidden_state: Tensor {
// dims: [ 1, 1144, 1024 ],
// type: 'float32',
// data: Float32Array(1171456) [ ... ],
// size: 1171456
// }
// }
Kind: static class of models
models.WavLMPreTrainedModel
An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.
Kind: static class of models
models.WavLMModel
The bare WavLM Model transformer outputting raw hidden-states without any specific head on top.
Example: Load and run an WavLMModel
for feature extraction.
Copied
import { AutoProcessor, AutoModel, read_audio } from '@xenova/transformers';
// Read and preprocess audio
const processor = await AutoProcessor.from_pretrained('Xenova/wavlm-base');
const audio = await read_audio('https://boincai.com/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav', 16000);
const inputs = await processor(audio);
// Run model with inputs
const model = await AutoModel.from_pretrained('Xenova/wavlm-base');
const output = await model(inputs);
// {
// last_hidden_state: Tensor {
// dims: [ 1, 549, 768 ],
// type: 'float32',
// data: Float32Array(421632) [-0.349443256855011, -0.39341306686401367, 0.022836603224277496, ...],
// size: 421632
// }
// }
Kind: static class of models
models.WavLMForCTC
WavLM Model with a language modeling
head on top for Connectionist Temporal Classification (CTC).
Kind: static class of models
wavLMForCTC._call(model_inputs)
Kind: instance method of WavLMForCTC
model_inputs
Object
model_inputs.input_values
Tensor
Float values of input raw speech waveform.
model_inputs.attention_mask
Tensor
Mask to avoid performing convolution and attention on padding token indices. Mask values selected in [0, 1]
models.WavLMForSequenceClassification
WavLM Model with a sequence classification head on top (a linear layer over the pooled output).
Kind: static class of models
wavLMForSequenceClassification._call(model_inputs) ⇒ <code> Promise. < SequenceClassifierOutput > </code>
Calls the model on new inputs.
Kind: instance method of WavLMForSequenceClassification
Returns: Promise.<SequenceClassifierOutput>
- An object containing the model’s output logits for sequence classification.
model_inputs
Object
The inputs to the model.
models.SpeechT5PreTrainedModel
An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.
Kind: static class of models
models.SpeechT5Model
The bare SpeechT5 Encoder-Decoder Model outputting raw hidden-states without any specific pre- or post-nets.
Kind: static class of models
models.SpeechT5ForSpeechToText
SpeechT5 Model with a speech encoder and a text decoder.
Kind: static class of models
models.SpeechT5ForTextToSpeech
SpeechT5 Model with a text encoder and a speech decoder.
Kind: static class of models
new SpeechT5ForTextToSpeech(config, session, decoder_merged_session, generation_config)
Creates a new instance of the SpeechT5ForTextToSpeech
class.
config
Object
The model configuration.
session
any
session for the model.
decoder_merged_session
any
session for the decoder.
generation_config
GenerationConfig
The generation configuration.
speechT5ForTextToSpeech.generate_speech(input_values, speaker_embeddings, options) ⇒ <code> Promise. < SpeechOutput > </code>
Converts a sequence of input tokens into a sequence of mel spectrograms, which are subsequently turned into a speech waveform using a vocoder.
Kind: instance method of SpeechT5ForTextToSpeech
Returns: Promise.<SpeechOutput>
- A promise which resolves to an object containing the spectrogram, waveform, and cross-attention tensors.
input_values
Tensor
Indices of input sequence tokens in the vocabulary.
speaker_embeddings
Tensor
Tensor containing the speaker embeddings.
options
Object
Optional parameters for generating speech.
[options.threshold]
number
0.5
The generated sequence ends when the predicted stop token probability exceeds this value.
[options.minlenratio]
number
0.0
Used to calculate the minimum required length for the output sequence.
[options.maxlenratio]
number
20.0
Used to calculate the maximum allowed length for the output sequence.
[options.vocoder]
Object
The vocoder that converts the mel spectrogram into a speech waveform. If null
, the output is the mel spectrogram.
[options.output_cross_attentions]
boolean
false
Whether or not to return the attentions tensors of the decoder's cross-attention layers.
models.SpeechT5HifiGan
HiFi-GAN vocoder.
Kind: static class of models
models.PretrainedMixin
Base class of all AutoModels. Contains the from_pretrained
function which is used to instantiate pretrained models.
Kind: static class of models
instance
static
.from_pretrained()
:PreTrainedModel.from_pretrained
pretrainedMixin.MODEL_CLASS_MAPPINGS : <code> * </code>
Mapping from model type to model class.
Kind: instance property of PretrainedMixin
pretrainedMixin.BASE_IF_FAIL
Whether to attempt to instantiate the base class (PretrainedModel
) if the model type is not found in the mapping.
Kind: instance property of PretrainedMixin
PretrainedMixin.from_pretrained() : <code> PreTrainedModel.from_pretrained </code>
Kind: static method of PretrainedMixin
models.AutoModel
Helper class which is used to instantiate pretrained models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForSequenceClassification
Helper class which is used to instantiate pretrained sequence classification models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForTokenClassification
Helper class which is used to instantiate pretrained token classification models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForSeq2SeqLM
Helper class which is used to instantiate pretrained sequence-to-sequence models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForSpeechSeq2Seq
Helper class which is used to instantiate pretrained sequence-to-sequence speech-to-text models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForTextToSpectrogram
Helper class which is used to instantiate pretrained sequence-to-sequence text-to-spectrogram models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForCausalLM
Helper class which is used to instantiate pretrained causal language models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForMaskedLM
Helper class which is used to instantiate pretrained masked language models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForQuestionAnswering
Helper class which is used to instantiate pretrained question answering models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForVision2Seq
Helper class which is used to instantiate pretrained vision-to-sequence models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForImageClassification
Helper class which is used to instantiate pretrained image classification models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForImageSegmentation
Helper class which is used to instantiate pretrained image segmentation models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForObjectDetection
Helper class which is used to instantiate pretrained object detection models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.AutoModelForMaskGeneration
Helper class which is used to instantiate pretrained object detection models with the from_pretrained
function. The chosen model class is determined by the type specified in the model config.
Kind: static class of models
models.Seq2SeqLMOutput
Kind: static class of models
new Seq2SeqLMOutput(output)
output
Object
The output of the model.
output.logits
Tensor
The output logits of the model.
output.past_key_values
Tensor
An tensor of key/value pairs that represent the previous state of the model.
output.encoder_outputs
Tensor
The output of the encoder in a sequence-to-sequence model.
[output.decoder_attentions]
Tensor
Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
[output.cross_attentions]
Tensor
Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
models.SequenceClassifierOutput
Base class for outputs of sentence classification models.
Kind: static class of models
new SequenceClassifierOutput(output)
output
Object
The output of the model.
output.logits
Tensor
classification (or regression if config.num_labels==1) scores (before SoftMax).
models.TokenClassifierOutput
Base class for outputs of token classification models.
Kind: static class of models
new TokenClassifierOutput(output)
output
Object
The output of the model.
output.logits
Tensor
Classification scores (before SoftMax).
models.MaskedLMOutput
Base class for masked language models outputs.
Kind: static class of models
new MaskedLMOutput(output)
output
Object
The output of the model.
output.logits
Tensor
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
models.QuestionAnsweringModelOutput
Base class for outputs of question answering models.
Kind: static class of models
new QuestionAnsweringModelOutput(output)
output
Object
The output of the model.
output.start_logits
Tensor
Span-start scores (before SoftMax).
output.end_logits
Tensor
Span-end scores (before SoftMax).
models.CausalLMOutput
Base class for causal language model (or autoregressive) outputs.
Kind: static class of models
new CausalLMOutput(output)
output
Object
The output of the model.
output.logits
Tensor
Prediction scores of the language modeling head (scores for each vocabulary token before softmax).
models.CausalLMOutputWithPast
Base class for causal language model (or autoregressive) outputs.
Kind: static class of models
new CausalLMOutputWithPast(output)
output
Object
The output of the model.
output.logits
Tensor
Prediction scores of the language modeling head (scores for each vocabulary token before softmax).
output.past_key_values
Tensor
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.
models~TypedArray : <code> * </code>
Kind: inner typedef of models
models~DecoderOutput ⇒ <code> Promise. < (Array < Array < number > > |EncoderDecoderOutput|DecoderOutput) > </code>
Generates text based on the given inputs and generation configuration using the model.
Kind: inner typedef of models
Returns: Promise.<(Array<Array<number>>|EncoderDecoderOutput|DecoderOutput)>
- An array of generated output sequences, where each sequence is an array of token IDs.
Throws:
Error
Throws an error if the inputs array is empty.
inputs
Tensor
| Array
| TypedArray
An array of input token IDs.
generation_config
Object
| GenerationConfig
| null
The generation configuration to use. If null, default configuration will be used.
logits_processor
Object
| null
An optional logits processor to use. If null, a new LogitsProcessorList instance will be created.
options
Object
options
[options.inputs_attention_mask]
Object
An optional attention mask for the inputs.
models~WhisperGenerationConfig : <code> Object </code>
Kind: inner typedef of models
Extends: GenerationConfig
Properties
[return_timestamps]
boolean
Whether to return the timestamps with the text. This enables the WhisperTimestampsLogitsProcessor
.
[return_token_timestamps]
boolean
Whether to return token-level timestamps with the text. This can be used with or without the return_timestamps
option. To get word-level timestamps, use the tokenizer to group the tokens into words.
[num_frames]
number
The number of audio frames available in this chunk. This is only used generating word-level timestamps.
models~SpeechOutput : <code> Object </code>
Kind: inner typedef of models
Properties
[spectrogram]
Tensor
The predicted log-mel spectrogram of shape (output_sequence_length, config.num_mel_bins)
. Returned when no vocoder
is provided
[waveform]
Tensor
The predicted waveform of shape (num_frames,)
. Returned when a vocoder
is provided.
[cross_attentions]
Tensor
The outputs of the decoder's cross-attention layers of shape (config.decoder_layers, config.decoder_attention_heads, output_sequence_length, input_sequence_length)
. returned when output_cross_attentions
is true
.
Last updated