Transformers documentation

Utilities for Generation

Transformers

You are viewing v4.13.0 version. A newer version v4.46.3 is available.

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Utilities for Generation

This page lists all the utility functions used by generate(), greedy_search(), sample(), beam_search(), beam_sample(), and group_beam_search().

Most of those are only useful if you are studying the code of the generate methods in the library.

Generate Outputs

The output of generate() is an instance of a subclass of ModelOutput. This output is a data structure containing all the information returned by generate(), but that can also be used as tuple or dictionary.

Here’s an example:

from transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2LMHeadModel.from_pretrained('gpt2')

inputs = tokenizer("Hello, my dog is cute and ", return_tensors="pt")
generation_output = model.generate(**inputs, return_dict_in_generate=True, output_scores=True)

The generation_output object is a GreedySearchDecoderOnlyOutput, as we can see in the documentation of that class below, it means it has the following attributes:

sequences: the generated sequences of tokens
scores (optional): the prediction scores of the language modelling head, for each generation step
hidden_states (optional): the hidden states of the model, for each generation step
attentions (optional): the attention weights of the model, for each generation step

Here we have the scores since we passed along output_scores=True, but we don’t have hidden_states and attentions because we didn’t pass output_hidden_states=True or output_attentions=True.

You can access each attribute as you would usually do, and if that attribute has not been returned by the model, you will get None. Here for instance generation_output.scores are all the generated prediction scores of the language modeling head, and generation_output.attentions is None.

When using our generation_output object as a tuple, it only keeps the attributes that don’t have None values. Here, for instance, it has two elements, loss then logits, so

generation_output[:2]

will return the tuple (generation_output.sequences, generation_output.scores) for instance.

When using our generation_output object as a dictionary, it only keeps the attributes that don’t have None values. Here, for instance, it has two keys that are sequences and scores.

We document here all output types.

GreedySearchOutput

class transformers.generation_utils.GreedySearchDecoderOnlyOutput < source >

( sequences: LongTensor = None scores: typing.Optional[typing.Tuple[torch.FloatTensor]] = None attentions: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None hidden_states: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None )

Parameters

sequences (torch.LongTensor of shape (batch_size, sequence_length)) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
scores (tuple(torch.FloatTensor) optional, returned when output_scores=True is passed or when config.output_scores=True) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. (max_length-input_ids.shape[-1],)-shaped tuple of torch.FloatTensor with each tensor of shape (batch_size, config.vocab_size)).
attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size, num_heads, generated_length, sequence_length).
hidden_states (tuple(tuple(torch.FloatTensor)), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size, generated_length, hidden_size).

Base class for outputs of decoder-only generation models using greedy search.

class transformers.generation_utils.GreedySearchEncoderDecoderOutput < source >

( sequences: LongTensor = None scores: typing.Optional[typing.Tuple[torch.FloatTensor]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None decoder_attentions: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None cross_attentions: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None )

Parameters

sequences (torch.LongTensor of shape (batch_size, sequence_length)) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
scores (tuple(torch.FloatTensor) optional, returned when output_scores=True is passed or when config.output_scores=True) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. (max_length-1,)-shaped tuple of torch.FloatTensor with each tensor of shape (batch_size, config.vocab_size)).
encoder_attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer of the decoder) of shape (batch_size, num_heads, sequence_length, sequence_length).
encoder_hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).
decoder_attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size, num_heads, generated_length, sequence_length).
cross_attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size, num_heads, generated_length, sequence_length).
decoder_hidden_states (tuple(tuple(torch.FloatTensor)), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size, generated_length, hidden_size).

Base class for outputs of encoder-decoder generation models using greedy search. Hidden states and attention weights of the decoder (respectively the encoder) can be accessed via the encoder_attentions and the encoder_hidden_states attributes (respectively the decoder_attentions and the decoder_hidden_states attributes)

class transformers.generation_flax_utils.FlaxGreedySearchOutput < source >

( sequences: ndarray = None )

Parameters

sequences (jnp.ndarray of shape (batch_size, max_length)) — The generated sequences.

Flax Base class for outputs of decoder-only generation models using greedy search.

replace < source >

( **updates )

“Returns a new object replacing the specified fields with new values.

SampleOutput

class transformers.generation_utils.SampleDecoderOnlyOutput < source >

Parameters

sequences (torch.LongTensor of shape (batch_size*num_return_sequences, sequence_length)) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
scores (tuple(torch.FloatTensor) optional, returned when output_scores=True is passed or when config.output_scores=True) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. (max_length-input_ids.shape[-1],)-shaped tuple of torch.FloatTensor with each tensor of shape (batch_size*num_return_sequences, config.vocab_size)).
attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (num_return_sequences*batch_size, num_heads, generated_length, sequence_length).
hidden_states (tuple(tuple(torch.FloatTensor)), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (num_return_sequences*batch_size, generated_length, hidden_size).

Base class for outputs of decoder-only generation models using sampling.

class transformers.generation_utils.SampleEncoderDecoderOutput < source >

Parameters

sequences (torch.LongTensor of shape (batch_size*num_return_sequences, sequence_length)) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
scores (tuple(torch.FloatTensor) optional, returned when output_scores=True is passed or when config.output_scores=True) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. (max_length-1,)-shaped tuple of torch.FloatTensor with each tensor of shape (batch_size*num_return_sequences, config.vocab_size)).
encoder_attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer of the decoder) of shape (batch_size*num_return_sequences, num_heads, sequence_length, sequence_length).
encoder_hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size*num_return_sequences, sequence_length, hidden_size).
decoder_attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_return_sequences, num_heads, generated_length, sequence_length).
cross_attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size, num_heads, generated_length, sequence_length).
decoder_hidden_states (tuple(tuple(torch.FloatTensor)), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_return_sequences, generated_length, hidden_size).

Base class for outputs of encoder-decoder generation models using sampling. Hidden states and attention weights of the decoder (respectively the encoder) can be accessed via the encoder_attentions and the encoder_hidden_states attributes (respectively the decoder_attentions and the decoder_hidden_states attributes)

class transformers.generation_flax_utils.FlaxSampleOutput < source >

( sequences: ndarray = None )

Parameters

sequences (jnp.ndarray of shape (batch_size, max_length)) — The generated sequences.

Flax Base class for outputs of decoder-only generation models using sampling.

replace < source >

( **updates )

“Returns a new object replacing the specified fields with new values.

BeamSearchOutput

class transformers.generation_utils.BeamSearchDecoderOnlyOutput < source >

( sequences: LongTensor = None sequences_scores: typing.Optional[torch.FloatTensor] = None scores: typing.Optional[typing.Tuple[torch.FloatTensor]] = None attentions: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None hidden_states: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None )

Parameters

sequences (torch.LongTensor of shape (batch_size*num_return_sequences, sequence_length)) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
sequences_scores (torch.FloatTensor of shape (batch_size*num_return_sequences), optional, returned when output_scores=True is passed or when config.output_scores=True) — Final beam scores of the generated sequences.
scores (tuple(torch.FloatTensor) optional, returned when output_scores=True is passed or when config.output_scores=True) — Processed beam scores for each vocabulary token at each generation step. Beam scores consisting of log softmax scores for each vocabulary token and sum of log softmax of previously generated tokens in this beam . (max_length-input_ids.shape[-1],)-shaped tuple of torch.FloatTensor with each tensor of shape (batch_size*num_beams*num_return_sequences, config.vocab_size)).
attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_beams, num_heads, generated_length, sequence_length).
hidden_states (tuple(tuple(torch.FloatTensor)), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_beams*num_return_sequences, generated_length, hidden_size).

Base class for outputs of decoder-only generation models using beam search.

class transformers.generation_utils.BeamSearchEncoderDecoderOutput < source >

( sequences: LongTensor = None sequences_scores: typing.Optional[torch.FloatTensor] = None scores: typing.Optional[typing.Tuple[torch.FloatTensor]] = None encoder_attentions: typing.Optional[typing.Tuple[torch.FloatTensor]] = None encoder_hidden_states: typing.Optional[typing.Tuple[torch.FloatTensor]] = None decoder_attentions: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None cross_attentions: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None )

Parameters

sequences (torch.LongTensor of shape (batch_size*num_return_sequences, sequence_length)) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
sequences_scores (torch.FloatTensor of shape (batch_size*num_return_sequences), optional, returned when output_scores=True is passed or when config.output_scores=True) — Final beam scores of the generated sequences.
scores (tuple(torch.FloatTensor) optional, returned when output_scores=True is passed or when config.output_scores=True) — Processed beam scores for each vocabulary token at each generation step. Beam scores consisting of log softmax scores for each vocabulary token and sum of log softmax of previously generated tokens in this beam . (max_length-1,)-shaped tuple of torch.FloatTensor with each tensor of shape (batch_size*num_beams, config.vocab_size)).
attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) —
encoder_attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer of the decoder) of shape (batch_size, num_heads, sequence_length, sequence_length).
encoder_hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size*num_beams*num_return_sequences, sequence_length, hidden_size).
decoder_attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_beams*num_return_sequences, num_heads, generated_length, sequence_length).
cross_attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size, num_heads, generated_length, sequence_length).
decoder_hidden_states (tuple(tuple(torch.FloatTensor)), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_beams*num_return_sequences, generated_length, hidden_size).

Base class for outputs of encoder-decoder generation models using beam search. Hidden states and attention weights of the decoder (respectively the encoder) can be accessed via the encoder_attentions and the encoder_hidden_states attributes (respectively the decoder_attentions and the decoder_hidden_states attributes)

BeamSampleOutput

class transformers.generation_utils.BeamSampleDecoderOnlyOutput < source >

Parameters

sequences (torch.LongTensor of shape (batch_size*num_return_sequences, sequence_length)) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
sequences_scores (torch.FloatTensor of shape (batch_size * num_return_sequence), optional, returned when output_scores=True is passed or when config.output_scores=True) — Final beam scores of the generated sequences.
scores (tuple(torch.FloatTensor) optional, returned when output_scores=True is passed or when config.output_scores=True) — Processed beam scores for each vocabulary token at each generation step. Beam scores consisting of log softmax scores for each vocabulary token and sum of log softmax of previously generated tokens in this beam . (max_length-input_ids.shape[-1],)-shaped tuple of torch.FloatTensor with each tensor of shape (batch_size*num_beams*num_return_sequences, config.vocab_size)).
attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_beams, num_heads, generated_length, sequence_length).
hidden_states (tuple(tuple(torch.FloatTensor)), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_beams, generated_length, hidden_size).

Base class for outputs of decoder-only generation models using beam sample.

class transformers.generation_utils.BeamSampleEncoderDecoderOutput < source >

Parameters

sequences (torch.LongTensor of shape (batch_size*num_beams, sequence_length)) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
sequences_scores (torch.FloatTensor of shape (batch_size * num_return_sequence), optional, returned when output_scores=True is passed or when config.output_scores=True) — Final beam scores of the generated sequences.
scores (tuple(torch.FloatTensor) optional, returned when output_scores=True is passed or when config.output_scores=True) — Processed beam scores for each vocabulary token at each generation step. Beam scores consisting of log softmax scores for each vocabulary token and sum of log softmax of previously generated tokens in this beam . (max_length-1,)-shaped tuple of torch.FloatTensor with each tensor of shape (batch_size*num_beams, config.vocab_size)).
encoder_attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer of the decoder) of shape (batch_size, num_heads, sequence_length, sequence_length).
encoder_hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size*num_beams, sequence_length, hidden_size).
decoder_attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_beams, num_heads, generated_length, sequence_length).
cross_attentions (tuple(tuple(torch.FloatTensor)), optional, returned when output_attentions=True is passed or config.output_attentions=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size, num_heads, generated_length, sequence_length).
decoder_hidden_states (tuple(tuple(torch.FloatTensor)), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of torch.FloatTensor of shape (batch_size*num_beams, generated_length, hidden_size).

Base class for outputs of encoder-decoder generation models using beam sampling. Hidden states and attention weights of the decoder (respectively the encoder) can be accessed via the encoder_attentions and the encoder_hidden_states attributes (respectively the decoder_attentions and the decoder_hidden_states attributes)

LogitsProcessor

A LogitsProcessor can be used to modify the prediction scores of a language model head for generation.

class transformers.LogitsProcessor < source >

( )

Abstract base class for all logit processors that can be applied during generation.

__call__ < source >

( input_ids: LongTensor scores: FloatTensor ) → torch.FloatTensor of shape (batch_size, config.vocab_size)

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (torch.FloatTensor of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be logits for each vocabulary when not using beam search or log softmax for each vocabulary token when using beam search kwargs — Additional logits processor specific kwargs.

Returns

torch.FloatTensor of shape (batch_size, config.vocab_size)

The processed prediction scores.

Torch method for processing logits.

class transformers.LogitsProcessorList < source >

( iterable = () )

This class can be used to create a list of LogitsProcessor or LogitsWarper to subsequently process a scores input tensor. This class inherits from list and adds a specific call method to apply each LogitsProcessor or LogitsWarper to the inputs.

__call__ < source >

( input_ids: LongTensor scores: FloatTensor **kwargs ) → torch.FloatTensor of shape (batch_size, config.vocab_size)

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (torch.FloatTensor of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be logits for each vocabulary when not using beam search or log softmax for each vocabulary token when using beam search kwargs — Additional logits processor specific kwargs.

Returns

torch.FloatTensor of shape (batch_size, config.vocab_size)

The processed prediction scores.

class transformers.LogitsWarper < source >

( )

Abstract base class for all logit warpers that can be applied during generation with multinomial sampling.

__call__ < source >

( input_ids: LongTensor scores: FloatTensor ) → torch.FloatTensor of shape (batch_size, config.vocab_size)

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (torch.FloatTensor of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be logits for each vocabulary when not using beam search or log softmax for each vocabulary token when using beam search kwargs — Additional logits processor specific kwargs.

Returns

torch.FloatTensor of shape (batch_size, config.vocab_size)

The processed prediction scores.

Torch method for warping logits.

class transformers.MinLengthLogitsProcessor < source >

( min_length: int eos_token_id: int )

Parameters

min_length (int) — The minimum length below which the score of eos_token_id is set to -float("Inf").
eos_token_id (int) — The id of the end-of-sequence token.

transformers.LogitsProcessor enforcing a min-length by setting EOS probability to 0.

class transformers.TemperatureLogitsWarper < source >

( temperature: float )

Parameters

temperature (float) — The value used to module the logits distribution.

transformers.LogitsWarper for temperature (exponential scaling output probability distribution).

class transformers.RepetitionPenaltyLogitsProcessor < source >

( penalty: float )

Parameters

repetition_penalty (float) — The parameter for repetition penalty. 1.0 means no penalty. See this paper for more details.

transformers.LogitsProcessor enforcing an exponential penalty on repeated sequences.

class transformers.TopPLogitsWarper < source >

( top_p: float filter_value: float = -inf min_tokens_to_keep: int = 1 )

Parameters

top_p (float) — If set to < 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation.
filter_value (float, optional, defaults to -float("Inf")) — All filtered values will be set to this float value.
min_tokens_to_keep (int, optional, defaults to 1) — Minimum number of tokens that cannot be filtered.

transformers.LogitsWarper that performs top-p, i.e. restricting to top tokens summing to prob_cut_off <= prob_cut_off.

class transformers.TopKLogitsWarper < source >

( top_k: int filter_value: float = -inf min_tokens_to_keep: int = 1 )

Parameters

top_k (int) — The number of highest probability vocabulary tokens to keep for top-k-filtering.
filter_value (float, optional, defaults to -float("Inf")) — All filtered values will be set to this float value.
min_tokens_to_keep (int, optional, defaults to 1) — Minimum number of tokens that cannot be filtered.

transformers.LogitsWarper that performs top-k, i.e. restricting to the k highest probability elements.

class transformers.NoRepeatNGramLogitsProcessor < source >

( ngram_size: int )

Parameters

ngram_size (int) — All ngrams of size ngram_size can only occur once.

transformers.LogitsProcessor that enforces no repetition of n-grams. See Fairseq.

class transformers.NoBadWordsLogitsProcessor < source >

( bad_words_ids: typing.List[typing.List[int]] eos_token_id: int )

Parameters

bad_words_ids (List[List[int]]) — List of list of token ids that are not allowed to be generated. In order to get the tokens of the words that should not appear in the generated text, use tokenizer(bad_word, add_prefix_space=True).input_ids.
eos_token_id (int) — The id of the end-of-sequence token.

transformers.LogitsProcessor that enforces that specified sequences will never be sampled.

class transformers.PrefixConstrainedLogitsProcessor < source >

( prefix_allowed_tokens_fn: typing.Callable[[int, torch.Tensor], typing.List[int]] num_beams: int )

transformers.LogitsProcessor that enforces constrained generation and is useful for prefix-conditioned constrained generation. See Autoregressive Entity Retrieval for more information.

class transformers.HammingDiversityLogitsProcessor < source >

( diversity_penalty: float num_beams: int num_beam_groups: int )

Parameters

diversity_penalty (float) — This value is subtracted from a beam’s score if it generates a token same as any beam from other group at a particular time. Note that diversity_penalty is only effective if group beam search is enabled.
num_beams (int) — Number of beams used for group beam search. See this paper for more details.
num_beam_groups (int) — Number of groups to divide num_beams into in order to ensure diversity among different groups of beams. See this paper for more details.

transformers.LogitsProcessor that enforces diverse beam search. Note that this logits processor is only effective for transformers.PreTrainedModel.group_beam_search(). See Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models for more details.

class transformers.ForcedBOSTokenLogitsProcessor < source >

( bos_token_id: int )

Parameters

bos_token_id (int) — The id of the token to force as the first generated token.

LogitsProcessor that enforces the specified token as the first generated token.

class transformers.ForcedEOSTokenLogitsProcessor < source >

( max_length: int eos_token_id: int )

Parameters

max_length (int) — The maximum length of the sequence to be generated.
eos_token_id (int) — The id of the token to force as the last generated token when max_length is reached.

LogitsProcessor that enforces the specified token as the last generated token when max_length is reached.

class transformers.InfNanRemoveLogitsProcessor < source >

( )

LogitsProcessor that removes all nan and inf values to avoid the generation method to fail. Note that using the logits processor should only be used if necessary since it can slow down the generation method. max_length is reached.

class transformers.FlaxLogitsProcessor < source >

( )

Abstract base class for all logit processors that can be applied during generation.

__call__ < source >

( input_ids: ndarray scores: ndarray ) → jnp.ndarray of shape (batch_size, config.vocab_size)

Parameters

input_ids (jnp.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (jnp.ndarray of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be logits for each vocabulary when not using beam search or log softmax for each vocabulary token when using beam search kwargs — Additional logits processor specific kwargs.

Returns

jnp.ndarray of shape (batch_size, config.vocab_size)

The processed prediction scores.

Flax method for processing logits.

class transformers.FlaxLogitsProcessorList < source >

( iterable = () )

This class can be used to create a list of FlaxLogitsProcessor or FlaxLogitsWarper to subsequently process a scores input tensor. This class inherits from list and adds a specific call method to apply each FlaxLogitsProcessor or FlaxLogitsWarper to the inputs.

__call__ < source >

( input_ids: ndarray scores: ndarray cur_len: int **kwargs ) → jnp.ndarray of shape (batch_size, config.vocab_size)

Parameters

input_ids (jnp.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (jnp.ndarray of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be logits for each vocabulary when not using beam search or log softmax for each vocabulary token when using beam search kwargs — Additional logits processor specific kwargs.

Returns

jnp.ndarray of shape (batch_size, config.vocab_size)

The processed prediction scores.

class transformers.FlaxLogitsWarper < source >

( )

Abstract base class for all logit warpers that can be applied during generation with multinomial sampling.

__call__ < source >

( input_ids: ndarray scores: ndarray ) → jnp.ndarray of shape (batch_size, config.vocab_size)

Parameters

input_ids (jnp.ndarray of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (jnp.ndarray of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be logits for each vocabulary when not using beam search or log softmax for each vocabulary token when using beam search kwargs — Additional logits processor specific kwargs.

Returns

jnp.ndarray of shape (batch_size, config.vocab_size)

The processed prediction scores.

Flax method for warping logits.

class transformers.FlaxTemperatureLogitsWarper < source >

( temperature: float )

Parameters

temperature (float) — The value used to module the logits distribution.

transformers.LogitsWarper for temperature (exponential scaling output probability distribution).

class transformers.FlaxTopPLogitsWarper < source >

( top_p: float filter_value: float = -inf min_tokens_to_keep: int = 1 )

Parameters

top_p (float) — If set to < 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation.
filter_value (float, optional, defaults to -float("Inf")) — All filtered values will be set to this float value.
min_tokens_to_keep (int, optional, defaults to 1) — Minimum number of tokens that cannot be filtered.

transformers.LogitsWarper that performs top-p, i.e. restricting to top tokens summing to prob_cut_off <= prob_cut_off.

class transformers.FlaxTopKLogitsWarper < source >

( top_k: int filter_value: float = -inf min_tokens_to_keep: int = 1 )

Parameters

top_k (int) — The number of highest probability vocabulary tokens to keep for top-k-filtering.
filter_value (float, optional, defaults to -float("Inf")) — All filtered values will be set to this float value.
min_tokens_to_keep (int, optional, defaults to 1) — Minimum number of tokens that cannot be filtered.

transformers.LogitsWarper that performs top-k, i.e. restricting to the k highest probability elements.

class transformers.FlaxForcedBOSTokenLogitsProcessor < source >

( bos_token_id: int )

Parameters

bos_token_id (int) — The id of the token to force as the first generated token.

FlaxLogitsProcessor that enforces the specified token as the first generated token.

class transformers.FlaxForcedEOSTokenLogitsProcessor < source >

( max_length: int eos_token_id: int )

Parameters

max_length (int) — The maximum length of the sequence to be generated.
eos_token_id (int) — The id of the token to force as the last generated token when max_length is reached.

FlaxLogitsProcessor that enforces the specified token as the last generated token when max_length is reached.

class transformers.FlaxMinLengthLogitsProcessor < source >

( min_length: int eos_token_id: int )

Parameters

min_length (int) — The minimum length below which the score of eos_token_id is set to -float("Inf").
eos_token_id (int) — The id of the end-of-sequence token.

transformers.FlaxLogitsProcessor enforcing a min-length by setting EOS probability to 0.

StoppingCriteria

A StoppingCriteria can be used to change when to stop generation (other than EOS token).

class transformers.StoppingCriteria < source >

( )

Abstract base class for all stopping criteria that can be applied during generation.

__call__ < source >

( input_ids: LongTensor scores: FloatTensor **kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (torch.FloatTensor of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be scores for each vocabulary token before SoftMax or scores for each vocabulary token after SoftMax. kwargs — Additional stopping criteria specific kwargs.

Returns

bool. False indicates we should continue, True indicates we should stop.

__call__ < source >

( input_ids: LongTensor scores: FloatTensor **kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (torch.FloatTensor of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be scores for each vocabulary token before SoftMax or scores for each vocabulary token after SoftMax. kwargs — Additional stopping criteria specific kwargs.

Returns

bool. False indicates we should continue, True indicates we should stop.

class transformers.MaxLengthCriteria < source >

( max_length: int )

Parameters

max_length (int) — The maximum length that the output sequence can have in number of tokens.

This class can be used to stop generation whenever the full generated number of tokens exceeds max_length. Keep in mind for decoder-only type of transformers, this will include the initial prompted tokens.

__call__ < source >

( input_ids: LongTensor scores: FloatTensor **kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (torch.FloatTensor of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be scores for each vocabulary token before SoftMax or scores for each vocabulary token after SoftMax. kwargs — Additional stopping criteria specific kwargs.

Returns

bool. False indicates we should continue, True indicates we should stop.

class transformers.MaxTimeCriteria < source >

( max_time: float initial_timestamp: typing.Optional[float] = None )

Parameters

max_time (float) — The maximum allowed time in seconds for the generation.
initial_time (float, optional, defaults to time.time()) — The start of the generation allowed time.

This class can be used to stop generation whenever the full generation exceeds some amount of time. By default, the time will start being counted when you initialize this function. You can override this by passing an initial_time.

__call__ < source >

( input_ids: LongTensor scores: FloatTensor **kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

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

What are input IDs?
scores (torch.FloatTensor of shape (batch_size, config.vocab_size)) — Prediction scores of a language modeling head. These can be scores for each vocabulary token before SoftMax or scores for each vocabulary token after SoftMax. kwargs — Additional stopping criteria specific kwargs.

Returns

bool. False indicates we should continue, True indicates we should stop.

BeamSearch

class transformers.BeamScorer < source >

( )

Abstract base class for all beam scorers that are used for beam_search() and beam_sample().

process < source >

( input_ids: LongTensor next_scores: FloatTensor next_tokens: LongTensor next_indices: LongTensor **kwargs ) → UserDict

Parameters

input_ids (torch.LongTensor of shape (batch_size * num_beams, sequence_length)) — Indices of input sequence tokens in the vocabulary.

Indices can be obtained using any class inheriting from PreTrainedTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.call() for details.

What are input IDs?
next_scores (torch.FloatTensor of shape (batch_size, 2 * num_beams)) — Current scores of the top 2 * num_beams non-finished beam hypotheses.
next_tokens (torch.LongTensor of shape (batch_size, 2 * num_beams)) — input_ids of the tokens corresponding to the top 2 * num_beams non-finished beam hypotheses.
next_indices (torch.LongTensor of shape (batch_size, 2 * num_beams)) — Beam indices indicating to which beam hypothesis the next_tokens correspond.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (int, optional) — The id of the end-of-sequence token.

Returns

UserDict

A dictionary composed of the fields as defined above:

next_beam_scores (torch.FloatTensor of shape (batch_size * num_beams)) — Updated scores of all non-finished beams.
next_beam_tokens (torch.FloatTensor of shape (batch_size * num_beams)) — Next tokens to be added to the non-finished beam_hypotheses.
next_beam_indices (torch.FloatTensor of shape (batch_size * num_beams)) — Beam indices indicating to which beam the next tokens shall be added.

finalize < source >

( input_ids: LongTensor next_scores: FloatTensor next_tokens: LongTensor next_indices: LongTensor max_length: int **kwargs ) → torch.LongTensor of shape (batch_size * num_return_sequences, sequence_length)

Parameters

input_ids (torch.LongTensor of shape (batch_size * num_beams, sequence_length)) — Indices of input sequence tokens in the vocabulary.

Indices can be obtained using any class inheriting from PreTrainedTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.call() for details.

What are input IDs?
final_beam_scores (torch.FloatTensor of shape (batch_size * num_beams)) — The final scores of all non-finished beams.
final_beam_tokens (torch.FloatTensor of shape (batch_size * num_beams)) — The last tokens to be added to the non-finished beam_hypotheses.
final_beam_indices (torch.FloatTensor of shape (batch_size * num_beams)) — The beam indices indicating to which beam the final_beam_tokens shall be added.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (int, optional) — The id of the end-of-sequence token.

Returns

torch.LongTensor of shape (batch_size * num_return_sequences, sequence_length)

The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.

class transformers.BeamSearchScorer < source >

( batch_size: int num_beams: int device: device length_penalty: typing.Optional[float] = 1.0 do_early_stopping: typing.Optional[bool] = False num_beam_hyps_to_keep: typing.Optional[int] = 1 num_beam_groups: typing.Optional[int] = 1 **kwargs )

Parameters

batch_size (int) — Batch Size of input_ids for which standard beam search decoding is run in parallel.
max_length (int) — The maximum length of the sequence to be generated.
num_beams (int) — Number of beams for beam search.
device (torch.device) — Defines the device type (e.g., "cpu" or "cuda") on which this instance of BeamSearchScorer will be allocated.
length_penalty (float, optional, defaults to 1.0) — Exponential penalty to the length. 1.0 means no penalty. Set to values < 1.0 in order to encourage the model to generate shorter sequences, to a value > 1.0 in order to encourage the model to produce longer sequences.
do_early_stopping (bool, optional, defaults to False) — Whether to stop the beam search when at least num_beams sentences are finished per batch or not.
num_beam_hyps_to_keep (int, optional, defaults to 1) — The number of beam hypotheses that shall be returned upon calling finalize.
num_beam_groups (int) — Number of groups to divide num_beams into in order to ensure diversity among different groups of beams. See this paper for more details.

transformers.BeamScorer implementing standard beam search decoding.

Adapted in part from Facebook’s XLM beam search code.

Reference for the diverse beam search algorithm and implementation Ashwin Kalyan’s DBS implementation

Utilities

transformers.top_k_top_p_filtering < source >

( logits: FloatTensor top_k: int = 0 top_p: float = 1.0 filter_value: float = -inf min_tokens_to_keep: int = 1 )

Parameters

top_k (int, optional, defaults to 0) — If > 0, only keep the top k tokens with highest probability (top-k filtering)
top_p (float, optional, defaults to 1.0) — If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751)
min_tokens_to_keep (int, optional, defaults to 1) — Minimumber of tokens we keep per batch example in the output.

Filter a distribution of logits using top-k and/or nucleus (top-p) filtering

From: https://gist.github.com/thomwolf/1a5a29f6962089e871b94cbd09daf317

transformers.tf_top_k_top_p_filtering < source >

( logits top_k = 0 top_p = 1.0 filter_value = -inf min_tokens_to_keep = 1 )

Parameters

top_k (int, optional, defaults to 0) — If > 0, only keep the top k tokens with highest probability (top-k filtering)
top_p (float, optional, defaults to 1.0) — If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751)
min_tokens_to_keep (int, optional, defaults to 1) — Minimumber of tokens we keep per batch example in the output.

Filter a distribution of logits using top-k and/or nucleus (top-p) filtering

From: https://gist.github.com/thomwolf/1a5a29f6962089e871b94cbd09daf317

←Utilities for Trainer General Utilities→