Utilities for Generation
This page lists all the utility functions used by generate().
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("openai-community/gpt2")
model = GPT2LMHeadModel.from_pretrained("openai-community/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 GenerateDecoderOnlyOutput, as we can
see in the documentation of that class below, it means it has the following attributes:
sequences
: the generated sequences of tokensscores
(optional): the prediction scores of the language modelling head, for each generation stephidden_states
(optional): the hidden states of the model, for each generation stepattentions
(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.
PyTorch
class transformers.generation.GenerateDecoderOnlyOutput
< source >( sequences: LongTensor = None scores: typing.Optional[typing.Tuple[torch.FloatTensor]] = None logits: 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 past_key_values: typing.Optional[typing.Tuple[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 tomax_length
or shorter if all batches finished early due to theeos_token_id
. - scores (
tuple(torch.FloatTensor)
optional, returned whenoutput_scores=True
) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftorch.FloatTensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - logits (
tuple(torch.FloatTensor)
optional, returned whenoutput_logits=True
) — Unprocessed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftorch.FloatTensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - attentions (
tuple(tuple(torch.FloatTensor))
, optional, returned whenoutput_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - hidden_states (
tuple(tuple(torch.FloatTensor))
, optional, returned whenoutput_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size, generated_length, hidden_size)
. - past_key_values (
tuple(tuple(torch.FloatTensor)))
, optional, returned whenuse_cache=True
) — Returns the model cache, used to speed up decoding. Different models have a different cache format, check the model’s documentation. Usually, a Cache instance.
Outputs of decoder-only generation models, when using non-beam methods.
class transformers.generation.GenerateEncoderDecoderOutput
< source >( sequences: LongTensor = None scores: typing.Optional[typing.Tuple[torch.FloatTensor]] = None logits: 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 past_key_values: typing.Optional[typing.Tuple[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 tomax_length
or shorter if all batches finished early due to theeos_token_id
. - scores (
tuple(torch.FloatTensor)
optional, returned whenoutput_scores=True
) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftorch.FloatTensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - logits (
tuple(torch.FloatTensor)
optional, returned whenoutput_logits=True
) — Unprocessed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftorch.FloatTensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - encoder_attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
) — Tuple oftorch.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 whenoutput_hidden_states=True
) — Tuple oftorch.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 whenoutput_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - cross_attentions (
tuple(tuple(torch.FloatTensor))
, optional, returned whenoutput_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - decoder_hidden_states (
tuple(tuple(torch.FloatTensor))
, optional, returned whenoutput_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size, generated_length, hidden_size)
. - past_key_values (
tuple(tuple(torch.FloatTensor)))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Returns the model cache, used to speed up decoding. Different models have a different cache format, check the model’s documentation. Usually, a Cache instance.
Outputs of encoder-decoder generation models, when using non-beam methods.
class transformers.generation.GenerateBeamDecoderOnlyOutput
< source >( sequences: LongTensor = None sequences_scores: typing.Optional[torch.FloatTensor] = None scores: typing.Optional[typing.Tuple[torch.FloatTensor]] = None logits: typing.Optional[typing.Tuple[torch.FloatTensor]] = None beam_indices: typing.Optional[torch.LongTensor] = None attentions: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None hidden_states: typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None past_key_values: typing.Optional[typing.Tuple[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 tomax_length
or shorter if all batches finished early due to theeos_token_id
. - sequences_scores (
torch.FloatTensor
of shape(batch_size*num_return_sequences)
, optional, returned whenoutput_scores=True
) — Final beam scores of the generatedsequences
. - scores (
tuple(torch.FloatTensor)
optional, returned whenoutput_scores=True
) — Beam transition scores for each vocabulary token at each generation step. Beam transition scores consisting of log probabilities of tokens conditioned on log softmax of previously generated tokens in this beam. Tuple oftorch.FloatTensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size*num_beams, config.vocab_size)
. - logits (
tuple(torch.FloatTensor)
optional, returned whenoutput_logits=True
) — Unprocessed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftorch.FloatTensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - beam_indices (
torch.LongTensor
, optional, returned whenoutput_scores=True
) — Beam indices of generated token id at each generation step.torch.LongTensor
of shape(batch_size*num_return_sequences, sequence_length)
. - attentions (
tuple(tuple(torch.FloatTensor))
, optional, returned whenoutput_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size*num_beams, num_heads, generated_length, sequence_length)
. - hidden_states (
tuple(tuple(torch.FloatTensor))
, optional, returned whenoutput_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size*num_beams*num_return_sequences, generated_length, hidden_size)
. - past_key_values (
tuple(tuple(torch.FloatTensor)))
, optional, returned whenuse_cache=True
) — Returns the model cache, used to speed up decoding. Different models have a different cache format, check the model’s documentation. Usually, a Cache instance.
Outputs of decoder-only generation models, when using beam methods.
class transformers.generation.GenerateBeamEncoderDecoderOutput
< source >( sequences: LongTensor = None sequences_scores: typing.Optional[torch.FloatTensor] = None scores: typing.Optional[typing.Tuple[torch.FloatTensor]] = None logits: typing.Optional[typing.Tuple[torch.FloatTensor]] = None beam_indices: typing.Optional[torch.LongTensor] = 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 past_key_values: typing.Optional[typing.Tuple[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 tomax_length
or shorter if all batches finished early due to theeos_token_id
. - sequences_scores (
torch.FloatTensor
of shape(batch_size*num_return_sequences)
, optional, returned whenoutput_scores=True
) — Final beam scores of the generatedsequences
. - scores (
tuple(torch.FloatTensor)
optional, returned whenoutput_scores=True
) — Beam transition scores for each vocabulary token at each generation step. Beam transition scores consisting of log probabilities of tokens conditioned on log softmax of previously generated tokens in this beam. Tuple oftorch.FloatTensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size*num_beams, config.vocab_size)
. - logits (
tuple(torch.FloatTensor)
optional, returned whenoutput_logits=True
) — Unprocessed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftorch.FloatTensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - beam_indices (
torch.LongTensor
, optional, returned whenoutput_scores=True
) — Beam indices of generated token id at each generation step.torch.LongTensor
of shape(batch_size*num_return_sequences, sequence_length)
. - encoder_attentions (
tuple(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
) — Tuple oftorch.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 whenoutput_hidden_states=True
) — Tuple oftorch.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 whenoutput_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size*num_beams*num_return_sequences, num_heads, generated_length, sequence_length)
. - cross_attentions (
tuple(tuple(torch.FloatTensor))
, optional, returned whenoutput_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - decoder_hidden_states (
tuple(tuple(torch.FloatTensor))
, optional, returned whenoutput_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftorch.FloatTensor
of shape(batch_size*num_beams*num_return_sequences, generated_length, hidden_size)
. - past_key_values (
tuple(tuple(torch.FloatTensor)))
, optional, returned whenuse_cache=True
) — Returns the model cache, used to speed up decoding. Different models have a different cache format, check the model’s documentation. Usually, a Cache instance.
Outputs of encoder-decoder generation models, when using beam methods.
TensorFlow
class transformers.generation.TFGreedySearchEncoderDecoderOutput
< source >( sequences: Tensor = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None encoder_attentions: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None encoder_hidden_states: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None decoder_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None cross_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - encoder_attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple oftf.Tensor
(one for each layer of the decoder) of shape(batch_size, num_heads, sequence_length, sequence_length)
. - encoder_hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftf.Tensor
(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(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - cross_attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - decoder_hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
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.TFGreedySearchDecoderOnlyOutput
< source >( sequences: Tensor = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, generated_length, hidden_size)
.
Base class for outputs of decoder-only generation models using greedy search.
class transformers.generation.TFSampleEncoderDecoderOutput
< source >( sequences: Tensor = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None encoder_attentions: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None encoder_hidden_states: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None decoder_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None cross_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size*num_return_sequences, config.vocab_size)
. - encoder_attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple oftf.Tensor
(one for each layer of the decoder) of shape(batch_size*num_return_sequences, num_heads, sequence_length, sequence_length)
. - encoder_hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftf.Tensor
(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(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size*num_return_sequences, num_heads, generated_length, sequence_length)
. - cross_attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - decoder_hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
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.TFSampleDecoderOnlyOutput
< source >( sequences: Tensor = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size*num_return_sequences, config.vocab_size)
. - attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(num_return_sequences*batch_size, num_heads, generated_length, sequence_length)
. - hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
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.TFBeamSearchEncoderDecoderOutput
< source >( sequences: Tensor = None sequences_scores: typing.Optional[tensorflow.python.framework.tensor.Tensor] = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None beam_indices: typing.Optional[tensorflow.python.framework.tensor.Tensor] = None encoder_attentions: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None encoder_hidden_states: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None decoder_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None cross_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - sequences_scores (
tf.Tensor
of shape(batch_size*num_return_sequences)
, optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Final beam scores of the generatedsequences
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.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.Tuple of
tf.Tensorwith up to
max_new_tokenselements (one element for each generated token), with each tensor of shape
(batch_size*num_beams, config.vocab_size)`. - beam_indices (
tf.Tensor
, optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Beam indices of generated token id at each generation step.tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
. - encoder_attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple oftf.Tensor
(one for each layer of the decoder) of shape(batch_size, num_heads, sequence_length, sequence_length)
. - encoder_hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftf.Tensor
(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(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size*num_beams*num_return_sequences, num_heads, generated_length, sequence_length)
. - cross_attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - decoder_hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
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)
class transformers.generation.TFBeamSearchDecoderOnlyOutput
< source >( sequences: Tensor = None sequences_scores: typing.Optional[tensorflow.python.framework.tensor.Tensor] = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None beam_indices: typing.Optional[tensorflow.python.framework.tensor.Tensor] = None attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - sequences_scores (
tf.Tensor
of shape(batch_size*num_return_sequences)
, optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Final beam scores of the generatedsequences
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.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. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size*num_beams*num_return_sequences, config.vocab_size)
. - beam_indices (
tf.Tensor
, optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Beam indices of generated token id at each generation step.tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
. - attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size*num_beams, num_heads, generated_length, sequence_length)
. - hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
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.TFBeamSampleEncoderDecoderOutput
< source >( sequences: Tensor = None sequences_scores: typing.Optional[tensorflow.python.framework.tensor.Tensor] = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None beam_indices: typing.Optional[tensorflow.python.framework.tensor.Tensor] = None encoder_attentions: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None encoder_hidden_states: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None decoder_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None cross_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size*num_beams, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - sequences_scores (
tf.Tensor
of shape(batch_size * num_return_sequence)
, optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Final beam scores of the generatedsequences
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.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. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size*num_beams, config.vocab_size)
. - beam_indices (
tf.Tensor
, optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Beam indices of generated token id at each generation step.tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
. - encoder_attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple oftf.Tensor
(one for each layer of the decoder) of shape(batch_size, num_heads, sequence_length, sequence_length)
. - encoder_hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftf.Tensor
(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(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size*num_beams, num_heads, generated_length, sequence_length)
. - cross_attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - decoder_hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
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)
class transformers.generation.TFBeamSampleDecoderOnlyOutput
< source >( sequences: Tensor = None sequences_scores: typing.Optional[tensorflow.python.framework.tensor.Tensor] = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None beam_indices: typing.Optional[tensorflow.python.framework.tensor.Tensor] = None attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - sequences_scores (
tf.Tensor
of shape(batch_size * num_return_sequence)
, optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Final beam scores of the generatedsequences
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.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. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size*num_beams*num_return_sequences, config.vocab_size)
. - beam_indices (
tf.Tensor
, optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Beam indices of generated token id at each generation step.tf.Tensor
of shape(batch_size*num_return_sequences, sequence_length)
. - attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size*num_beams, num_heads, generated_length, sequence_length)
. - hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
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.TFContrastiveSearchEncoderDecoderOutput
< source >( sequences: Tensor = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None encoder_attentions: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None encoder_hidden_states: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None decoder_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None cross_attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None decoder_hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - encoder_attentions (
tuple(tf.Tensor)
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple oftf.Tensor
(one for each layer of the decoder) of shape(batch_size, num_heads, sequence_length, sequence_length)
. - encoder_hidden_states (
tuple(tf.Tensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple oftf.Tensor
(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(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - cross_attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - decoder_hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, generated_length, hidden_size)
.
Base class for outputs of encoder-decoder generation models using contrastive 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.TFContrastiveSearchDecoderOnlyOutput
< source >( sequences: Tensor = None scores: typing.Optional[typing.Tuple[tensorflow.python.framework.tensor.Tensor]] = None attentions: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None hidden_states: typing.Optional[typing.Tuple[typing.Tuple[tensorflow.python.framework.tensor.Tensor]]] = None )
Parameters
- sequences (
tf.Tensor
of shape(batch_size, sequence_length)
) — The generated sequences. The second dimension (sequence_length) is either equal tomax_length
or shorter if all batches finished early due to theeos_token_id
. - scores (
tuple(tf.Tensor)
optional, returned whenoutput_scores=True
is passed or whenconfig.output_scores=True
) — Processed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax) at each generation step. Tuple oftf.Tensor
with up tomax_new_tokens
elements (one element for each generated token), with each tensor of shape(batch_size, config.vocab_size)
. - attentions (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_attentions=True
is passed orconfig.output_attentions=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, num_heads, generated_length, sequence_length)
. - hidden_states (
tuple(tuple(tf.Tensor))
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) — Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) oftf.Tensor
of shape(batch_size, generated_length, hidden_size)
.
Base class for outputs of decoder-only generation models using contrastive search.
FLAX
class transformers.generation.FlaxSampleOutput
< source >( sequences: Array = None )
Flax Base class for outputs of decoder-only generation models using sampling.
“Returns a new object replacing the specified fields with new values.
class transformers.generation.FlaxGreedySearchOutput
< source >( sequences: Array = None )
Flax Base class for outputs of decoder-only generation models using greedy search.
“Returns a new object replacing the specified fields with new values.
class transformers.generation.FlaxBeamSearchOutput
< source >( sequences: Array = None scores: Array = None )
Flax Base class for outputs of decoder-only generation models using greedy search.
“Returns a new object replacing the specified fields with new values.
LogitsProcessor
A LogitsProcessor can be used to modify the prediction scores of a language model head for generation.
PyTorch
class transformers.AlternatingCodebooksLogitsProcessor
< source >( input_start_len: int semantic_vocab_size: int codebook_size: int )
LogitsProcessor enforcing alternated generation between the two codebooks of Bark.
This logits processor is exclusively compatible with Bark’s fine submodel. See the model documentation for examples.
class transformers.ClassifierFreeGuidanceLogitsProcessor
< source >( guidance_scale )
LogitsProcessor for classifier free guidance (CFG). The scores are split over the batch dimension,
where the first half correspond to the conditional logits (predicted from the input prompt) and the second half
correspond to the unconditional logits (predicted from an empty or ‘null’ prompt). The processor computes a
weighted average across the conditional and unconditional logits, parameterised by the guidance_scale
.
See the paper for more information.
This logits processor is exclusively compatible with MusicGen
Examples:
>>> from transformers import AutoProcessor, MusicgenForConditionalGeneration
>>> processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
>>> model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")
>>> inputs = processor(
... text=["80s pop track with bassy drums and synth", "90s rock song with loud guitars and heavy drums"],
... padding=True,
... return_tensors="pt",
... )
>>> audio_values = model.generate(**inputs, do_sample=True, guidance_scale=3, max_new_tokens=256)
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.EncoderNoRepeatNGramLogitsProcessor
< source >( encoder_ngram_size: int encoder_input_ids: LongTensor )
LogitsProcessor that works similarly to NoRepeatNGramLogitsProcessor, but applied exclusively to prevent the repetition of n-grams present in the prompt.
It was designed to promote chattiness in a language model, by preventing the generation of n-grams present in previous conversation rounds.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-560m")
>>> tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-560m")
>>> inputs = tokenizer("Alice: I love cats. What do you love?\nBob:", return_tensors="pt")
>>> # With greedy decoding, we see Bob repeating Alice's opinion. If Bob was a chatbot, it would be a poor one.
>>> outputs = model.generate(**inputs)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
Alice: I love cats. What do you love?
Bob: I love cats. What do you
>>> # With this logits processor, we can prevent Bob from repeating Alice's opinion.
>>> outputs = model.generate(**inputs, encoder_no_repeat_ngram_size=2)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
Alice: I love cats. What do you love?
Bob: My cats are very cute.
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.EncoderRepetitionPenaltyLogitsProcessor
< source >( penalty: float encoder_input_ids: LongTensor )
LogitsProcessor that works similarly to RepetitionPenaltyLogitsProcessor, but with an inverse penalty that is applied to the tokens present in the prompt. In other words, a penalty above 1.0 increases the odds of selecting tokens that were present in the prompt.
It was designed to avoid hallucination in input-grounded tasks, like summarization. Although originally intended for encoder-decoder models, it can also be used with decoder-only models like LLMs.
Examples:
>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-560m")
>>> model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-560m")
>>> inputs = tokenizer(["Alice and Bob. The third member's name was"], return_tensors="pt")
>>> gen_out = model.generate(**inputs)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
Alice and Bob. The third member's name was not mentioned.
>>> # With the `encoder_repetition_penalty` argument we can trigger this logits processor in `generate`, which can
>>> # promote the use of prompt tokens ("Bob" in this example)
>>> gen_out = model.generate(**inputs, encoder_repetition_penalty=1.2)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
Alice and Bob. The third member's name was Bob. The third member's name was Bob.
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.EpsilonLogitsWarper
< source >( epsilon: float filter_value: float = -inf min_tokens_to_keep: int = 1 )
Parameters
- epsilon (
float
) — If set to > 0, only the most tokens with probabilitiesepsilon
or higher are kept for generation. - filter_value (
float
, optional, defaults to -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.
LogitsProcessor that performs epsilon-sampling, i.e. restricting to tokens with prob >= epsilon
. Takes the
largest min_tokens_to_keep tokens if no tokens satisfy this constraint. See Truncation Sampling as Language Model
Desmoothing for more information.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> set_seed(1)
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer("A sequence: 1, 2", return_tensors="pt")
>>> # With sampling, the output is unexpected -- sometimes too unexpected.
>>> outputs = model.generate(**inputs, do_sample=True)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3 | < 4 (left-hand pointer) ;
<BLANKLINE>
<BLANKLINE>
>>> # With epsilon sampling, the output gets restricted to high-probability tokens. Note that this is similar to
>>> # Top P sampling, which restricts tokens based on their cumulative probability.
>>> # Pro tip: The paper recomends using `epsilon_cutoff` values between 3e-4 and 9e-4
>>> outputs = model.generate(**inputs, do_sample=True, epsilon_cutoff=0.1)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3, 4, 5, 6, 7, 8, 9
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.EtaLogitsWarper
< source >( epsilon: float filter_value: float = -inf min_tokens_to_keep: int = 1 device: str = 'cpu' )
Parameters
- epsilon (
float
) — A float value in the range (0, 1). Hyperparameter used to calculate the dynamic cutoff value,eta
. The suggested values from the paper ranges from 3e-4 to 4e-3 depending on the size of the model. - filter_value (
float
, optional, defaults to -inf) — All values that are found to be below the dynamic cutoff value,eta
, are set to this float value. This parameter is useful when logits need to be modified for very low probability tokens that should be excluded from generation entirely. - min_tokens_to_keep (
int
, optional, defaults to 1) — Specifies the minimum number of tokens that must be kept for generation, regardless of their probabilities. For example, ifmin_tokens_to_keep
is set to 1, at least one token will always be kept for generation, even if all tokens have probabilities below the cutoffeta
. - device (
str
, optional, defaults to"cpu"
) — The device to allocate the tensors.
LogitsProcessor that performs eta-sampling, a technique to filter out tokens with probabilities below a dynamic
cutoff value, eta
, which is calculated based on a combination of the hyperparameter epsilon
and the entropy of
the token probabilities, i.e. eta := min(epsilon, sqrt(epsilon * e^-entropy(probabilities)))
. Takes the largest
min_tokens_to_keep tokens if no tokens satisfy this constraint. It addresses the issue of poor quality in long
samples of text generated by neural language models leading to more coherent and fluent text. See Truncation
Sampling as Language Model Desmoothing for more information. Note: do_sample
must be set to True
for this LogitsProcessor
to work.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> set_seed(1)
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer("A sequence: 1, 2", return_tensors="pt")
>>> # With sampling, the output is unexpected -- sometimes too unexpected.
>>> outputs = model.generate(**inputs, do_sample=True)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3 | < 4 (left-hand pointer) ;
<BLANKLINE>
<BLANKLINE>
>>> # With eta sampling, the output gets restricted to high-probability tokens. You can see it as a dynamic form of
>>> # epsilon sampling that adapts its cutoff probability based on the entropy (high entropy = lower cutoff).
>>> # Pro tip: The paper recomends using `eta_cutoff` values between 3e-4 to 4e-3
>>> outputs = model.generate(**inputs, do_sample=True, eta_cutoff=0.1)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3, 4, 5, 6, 7, 8, 9
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.ExponentialDecayLengthPenalty
< source >( exponential_decay_length_penalty: typing.Tuple[int, float] eos_token_id: typing.Union[int, typing.List[int], torch.Tensor] input_ids_seq_length: int )
Parameters
- exponential_decay_length_penalty (
tuple(int, float)
) — This tuple shall consist of:(start_index, decay_factor)
wherestart_index
indicates where penalty starts anddecay_factor
represents the factor of exponential decay - eos_token_id (
Union[int, List[int], torch.Tensor]
) — The id(s) of the end-of-sequence token. - input_ids_seq_length (
int
) — The length of the input sequence.
LogitsProcessor that exponentially increases the score of the eos_token_id
after start_index
has been
reached. This allows generating shorter sequences without having a hard cutoff, allowing the eos_token
to be
predicted in a meaningful position.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> text = "Just wanted to let you know, I"
>>> inputs = tokenizer(text, return_tensors="pt")
>>> # Let's consider that we want short sentences, so we limit `max_length=30`. However, we observe that the answer
>>> # tends to end abruptly.
>>> set_seed(1)
>>> outputs = model.generate(**inputs, do_sample=True, temperature=0.9, max_length=30, pad_token_id=50256)
>>> print(tokenizer.batch_decode(outputs)[0])
Just wanted to let you know, I received a link to an ebook, the book How To Start A Social Network which was
published in 2010. Although
>>> # To promote the appearance of the EOS token at the right time, we add the `exponential_decay_length_penalty =
>>> # (start_index, decay_factor)`. Instead of cutting at max_tokens, the output comes to an end before and usually
>>> # with more meaning. What happens is that starting from `start_index` the EOS token score will be increased
>>> # by `decay_factor` exponentially. However, if you set a high decay factor, you may also end up with abruptly
>>> # ending sequences.
>>> set_seed(1)
>>> outputs = model.generate(
... **inputs,
... do_sample=True,
... temperature=0.9,
... max_length=30,
... pad_token_id=50256,
... exponential_decay_length_penalty=(15, 1.6),
... )
>>> print(tokenizer.batch_decode(outputs)[0])
Just wanted to let you know, I received a link to an ebook, the book How To Start A Social Network
which<|endoftext|>
>>> # With a small decay factor, you will have a higher chance of getting a meaningful sequence.
>>> set_seed(1)
>>> outputs = model.generate(
... **inputs,
... do_sample=True,
... temperature=0.9,
... max_length=30,
... pad_token_id=50256,
... exponential_decay_length_penalty=(15, 1.01),
... )
>>> print(tokenizer.batch_decode(outputs)[0])
Just wanted to let you know, I received a link to an ebook, the book How To Start A Social Network which was
published in 2010.<|endoftext|>
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.ForcedBOSTokenLogitsProcessor
< source >( bos_token_id: int )
LogitsProcessor that enforces the specified token as the first generated token. Used with encoder-decoder models.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
>>> model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-small")
>>> tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-small")
>>> inputs = tokenizer("Translate from English to German: I love cats.", return_tensors="pt")
>>> # By default, it continues generating according to the model's logits
>>> outputs = model.generate(**inputs, max_new_tokens=10)
>>> print(tokenizer.batch_decode(outputs)[0])
<pad> Ich liebe Kitty.</s>
>>> # We can use `forced_bos_token_id` to force the start of generation with an encoder-decoder model
>>> # (including forcing it to end straight away with an EOS token)
>>> outputs = model.generate(**inputs, max_new_tokens=10, forced_bos_token_id=tokenizer.eos_token_id)
>>> print(tokenizer.batch_decode(outputs)[0])
<pad></s>
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.ForcedEOSTokenLogitsProcessor
< source >( max_length: int eos_token_id: typing.Union[int, typing.List[int], torch.Tensor] device: str = 'cpu' )
LogitsProcessor that enforces the specified token as the last generated token when max_length
is reached.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer("A sequence: 1, 2, 3", return_tensors="pt")
>>> # By default, it continues generating according to the model's logits
>>> outputs = model.generate(**inputs, max_new_tokens=10)
>>> print(tokenizer.batch_decode(outputs)[0])
A sequence: 1, 2, 3, 4, 5, 6, 7, 8
>>> # `forced_eos_token_id` ensures the generation ends with a EOS token
>>> outputs = model.generate(**inputs, max_new_tokens=10, forced_eos_token_id=tokenizer.eos_token_id)
>>> print(tokenizer.batch_decode(outputs)[0])
A sequence: 1, 2, 3, 4, 5, 6, 7,<|endoftext|>
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
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. A higherdiversity_penalty
will enforce greater diversity among the beams. Adjusting this value can help strike a balance between diversity and natural likelihood. - num_beams (
int
) — Number of beams for beam search. 1 means no beam search. - num_beam_groups (
int
) — Number of groups to dividenum_beams
into in order to ensure diversity among different groups of beams. this paper for more details.
LogitsProcessor that enforces diverse beam search.
Note that this logits processor is only effective for PreTrainedModel.group_beam_search
. See Diverse Beam
Search: Decoding Diverse Solutions from Neural Sequence Models for more
details.
Traditional beam search often generates very similar sequences across different beams.
HammingDiversityLogitsProcessor
addresses this by penalizing beams that generate tokens already chosen by other
beams in the same time step.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
>>> import torch
>>> # Initialize the model and tokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-base")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("google-t5/t5-base")
>>> # A long text about the solar system
>>> text = (
... "The Solar System is a gravitationally bound system comprising the Sun and the objects that orbit it, "
... "either directly or indirectly. Of the objects that orbit the Sun directly, the largest are the eight "
... "planets, with the remainder being smaller objects, such as the five dwarf planets and small Solar System "
... "bodies. The Solar System formed 4.6 billion years ago from the gravitational collapse of a giant "
... "interstellar molecular cloud."
... )
>>> inputs = tokenizer("summarize: " + text, return_tensors="pt")
>>> # Generate diverse summary
>>> outputs_diverse = model.generate(
... **inputs,
... num_beam_groups=2,
... diversity_penalty=10.0,
... max_length=100,
... num_beams=4,
... num_return_sequences=2,
... )
>>> summaries_diverse = tokenizer.batch_decode(outputs_diverse, skip_special_tokens=True)
>>> # Generate non-diverse summary
>>> outputs_non_diverse = model.generate(
... **inputs,
... max_length=100,
... num_beams=4,
... num_return_sequences=2,
... )
>>> summary_non_diverse = tokenizer.batch_decode(outputs_non_diverse, skip_special_tokens=True)
>>> # With `diversity_penalty`, the resulting beams are much more diverse
>>> print(summary_non_diverse)
['the solar system formed 4.6 billion years ago from the collapse of a giant interstellar molecular cloud. of the objects that orbit the Sun directly, the largest are the eight planets.',
'the Solar System formed 4.6 billion years ago from the collapse of a giant interstellar molecular cloud. of the objects that orbit the Sun directly, the largest are the eight planets.']
>>> print(summaries_diverse)
['the solar system formed 4.6 billion years ago from the collapse of a giant interstellar molecular cloud. of the objects that orbit the Sun directly, the largest are the eight planets.',
'the solar system formed 4.6 billion years ago from the collapse of a giant interstellar molecular cloud. of the objects that orbit the Sun directly, the largest are the eight planets. the rest of the objects are smaller objects, such as the five dwarf planets and small solar system bodies.']
__call__
< source >( input_ids: LongTensor scores: FloatTensor current_tokens: LongTensor beam_group_idx: int ) → 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. 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 - current_tokens (
torch.LongTensor
of shape(batch_size)
) — Indices of input sequence tokens in the vocabulary, corresponding to the tokens selected by the other beam groups in the current generation step. - beam_group_idx (
int
) — The index of the beam group currently being processed.
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
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.
This logits processor has no generate
example, as there shouldn’t be a correct combination of flags that warrants
its use.
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
LogitsProcessor for normalizing the scores using log-softmax. It’s important to normalize the scores during beam search, after applying the logits processors or warpers, since the search algorithm used in this library doesn’t do it (it only does it before, but they may need re-normalization) but it still supposes that the scores are normalized when comparing the hypotheses.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> import torch
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer("A sequence: 1, 2, 3", return_tensors="pt")
>>> # By default, the scores are not normalized -- the sum of their exponentials is NOT a normalized probability
>>> # distribution, summing to 1
>>> outputs = model.generate(**inputs, return_dict_in_generate=True, output_scores=True)
>>> print(torch.allclose(torch.sum(torch.exp(outputs.scores[-1])), torch.Tensor((1.000,)), rtol=1e-4))
False
>>> # Normalizing them may have a positive impact on beam methods, or when using the scores on your application
>>> outputs = model.generate(**inputs, renormalize_logits=True, return_dict_in_generate=True, output_scores=True)
>>> print(torch.allclose(torch.sum(torch.exp(outputs.scores[-1])), torch.Tensor((1.000,)), rtol=1e-4))
True
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
This class can be used to create a list of LogitsProcessor to subsequently process a scores
input tensor.
This class inherits from list and adds a specific call method to apply each LogitsProcessor 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. 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 (
Dict[str, Any]
, optional) — Additional kwargs that are specific to a logits processor.
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.MinLengthLogitsProcessor
< source >( min_length: int eos_token_id: typing.Union[int, typing.List[int], torch.Tensor] device: str = 'cpu' )
LogitsProcessor enforcing a min-length by setting EOS probability to 0. Note that, for decoder-only models like most LLMs, the length includes the prompt.
Examples:
>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-560m")
>>> model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-560m")
>>> inputs = tokenizer("A number:", return_tensors="pt")
>>> gen_out = model.generate(**inputs)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
A number: one
>>> # setting `min_length` to a value smaller than the uncontrolled output length has no impact
>>> gen_out = model.generate(**inputs, min_length=3)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
A number: one
>>> # setting a larger `min_length` will force the model to generate beyond its natural ending point, which is not
>>> # necessarily incorrect
>>> gen_out = model.generate(**inputs, min_length=10)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
A number: one thousand, nine hundred and ninety-four
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.MinNewTokensLengthLogitsProcessor
< source >( prompt_length_to_skip: int min_new_tokens: int eos_token_id: typing.Union[int, typing.List[int], torch.Tensor] device: str = 'cpu' )
Parameters
- prompt_length_to_skip (
int
) — The input tokens length. Not a valid argument when used withgenerate
as it will automatically assign the input length. - min_new_tokens (
int
) — The minimum new tokens length below which the score ofeos_token_id
is set to-float("Inf")
. - eos_token_id (
Union[int, List[int], torch.Tensor]
) — The id(s) of the end-of-sequence token. - device (
str
, optional, defaults to"cpu"
) — The device to allocate the tensors.
LogitsProcessor enforcing a min-length of new tokens by setting EOS (End-Of-Sequence) token probability to 0. Contrarily to MinLengthLogitsProcessor, this processor ignores the prompt.
Examples:
>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-560m")
>>> model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-560m")
>>> inputs = tokenizer(["A number:"], return_tensors="pt")
>>> gen_out = model.generate(**inputs)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
A number: one
>>> # setting `min_new_tokens` will force the model to generate beyond its natural ending point, which is not
>>> # necessarily incorrect
>>> gen_out = model.generate(**inputs, min_new_tokens=2)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
A number: one thousand
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.MinPLogitsWarper
< source >( min_p: float filter_value: float = -inf min_tokens_to_keep: int = 1 )
Parameters
- min_p (
float
) — Minimum token probability, which will be scaled by the probability of the most likely token. It must be a value between 0 and 1. Typical values are in the 0.01-0.2 range, comparably selective as settingtop_p
in the 0.99-0.8 range (use the opposite of normaltop_p
values). - filter_value (
float
, optional, defaults to -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.
LogitsProcessor that performs min-p, i.e. keeps all tokens that are above a minimum probability, scaled by the probability of the most likely token. As a result, the filter becomes more agressive in the presence of high-probability tokens, which is a sign of a confident output that we shouldn’t deviate from.
Often used together with TemperatureLogitsWarper. Used as an alternative to TopPLogitsWarper and TopKLogitsWarper.
Created by @menhguin and @kalomaze (github handles). Code adapted from this external PR
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> set_seed(1)
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer("A sequence: 1, 2", return_tensors="pt")
>>> # With sampling, the output is unexpected -- sometimes too unexpected.
>>> outputs = model.generate(**inputs, do_sample=True)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3 | < 4 (left-hand pointer) ;
<BLANKLINE>
<BLANKLINE>
>>> # With `min_p` sampling, the output gets restricted to high-probability tokens.
>>> # Pro tip: In practice, LLMs use `min_p` in the 0.01-0.2 range.
>>> outputs = model.generate(**inputs, do_sample=True, min_p=0.1)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3, 4, 5, 6, 7, 8, 9
class transformers.NoBadWordsLogitsProcessor
< source >( bad_words_ids: typing.List[typing.List[int]] eos_token_id: typing.Union[int, typing.List[int], torch.Tensor, NoneType] = None )
LogitsProcessor that enforces that specified sequences will never be selected.
In order to get the token ids of the words that should not appear in the generated text, make sure to set
add_prefix_space=True
when initializing the tokenizer, and use tokenizer(bad_words, add_special_tokens=False).input_ids
. The add_prefix_space
argument is only supported for some slow tokenizers,
as fast tokenizers’ prefixing behaviours come from pre tokenizers
. Read more
here.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> inputs = tokenizer(["In a word, the cake is a"], return_tensors="pt")
>>> output_ids = model.generate(inputs["input_ids"], max_new_tokens=5, pad_token_id=tokenizer.eos_token_id)
>>> print(tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0])
In a word, the cake is a bit of a mess.
>>> # Now let's take the bad words out. Please note that the tokenizer is initialized differently
>>> tokenizer_with_prefix_space = AutoTokenizer.from_pretrained("openai-community/gpt2", add_prefix_space=True)
>>> def get_tokens_as_list(word_list):
... "Converts a sequence of words into a list of tokens"
... tokens_list = []
... for word in word_list:
... tokenized_word = tokenizer_with_prefix_space([word], add_special_tokens=False).input_ids[0]
... tokens_list.append(tokenized_word)
... return tokens_list
>>> bad_words_ids = get_tokens_as_list(word_list=["mess"])
>>> output_ids = model.generate(
... inputs["input_ids"], max_new_tokens=5, bad_words_ids=bad_words_ids, pad_token_id=tokenizer.eos_token_id
... )
>>> print(tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0])
In a word, the cake is a bit of a surprise.
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.NoRepeatNGramLogitsProcessor
< source >( ngram_size: int )
N-grams are groups of “n” consecutive words, characters, or tokens taken from a sequence of text. Given the sentence: “She runs fast”, the bi-grams (n=2) would be (“she”, “runs”) and (“runs”, “fast”). In text generation, avoiding repetitions of word sequences provides a more diverse output. This LogitsProcessor enforces no repetition of n-grams by setting the scores of banned tokens to negative infinity which eliminates those tokens from consideration when further processing the scores. Note that, for decoder-only models like most LLMs, the prompt is also considered to obtain the n-grams. Fairseq.
Use n-gram penalties with care. For instance, penalizing 2-grams (bigrams) in an article about the city of New York might lead to undesirable outcomes where the city’s name appears only once in the entire text. Reference
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer(["Today I"], return_tensors="pt")
>>> output = model.generate(**inputs)
>>> print(tokenizer.decode(output[0], skip_special_tokens=True))
Today I’m not sure if I’m going to be able to do it.
>>> # Now let's add ngram size using `no_repeat_ngram_size`. This stops the repetitions ("I’m") in the output.
>>> output = model.generate(**inputs, no_repeat_ngram_size=2)
>>> print(tokenizer.decode(output[0], skip_special_tokens=True))
Today I’m not sure if I can get a better understanding of the nature of this issue
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.PrefixConstrainedLogitsProcessor
< source >( prefix_allowed_tokens_fn: typing.Callable[[int, torch.Tensor], typing.List[int]] num_beams: int )
Parameters
- prefix_allowed_tokens_fn (
Callable[[int, torch.Tensor], List[int]]
) — This function constraints the beam search to allowed tokens only at each step. This function takes 2 argumentsinputs_ids
and the batch IDbatch_id
. It has to return a list with the allowed tokens for the next generation step conditioned on the previously generated tokensinputs_ids
and the batch IDbatch_id
.
LogitsProcessor that enforces constrained generation and is useful for prefix-conditioned constrained generation. See Autoregressive Entity Retrieval for more information.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-560m")
>>> tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-560m")
>>> inputs = tokenizer("Alice and Bob", return_tensors="pt")
>>> # By default, it continues generating according to the model's logits
>>> outputs = model.generate(**inputs, max_new_tokens=5)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
Alice and Bob are friends
>>> # We can contrain it with `prefix_allowed_tokens_fn` to force a certain behavior based on a prefix.
>>> # For instance, we can force an entire entity to be generated when its beginning is detected.
>>> entity = tokenizer(" Bob Marley", return_tensors="pt").input_ids[0] # 3 tokens
>>> def prefix_allowed_tokens_fn(batch_id, input_ids):
... '''
... Attempts to generate 'Bob Marley' when 'Bob' is detected.
... In this case, `batch_id` is not used, but you can set rules for each batch member.
... '''
... if input_ids[-1] == entity[0]:
... return [entity[1].item()]
... elif input_ids[-2] == entity[0] and input_ids[-1] == entity[1]:
... return [entity[2].item()]
... return list(range(tokenizer.vocab_size)) # If no match, allow all tokens
>>> outputs = model.generate(**inputs, max_new_tokens=5, prefix_allowed_tokens_fn=prefix_allowed_tokens_fn)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
Alice and Bob Marley
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.RepetitionPenaltyLogitsProcessor
< source >( penalty: float )
LogitsProcessor that prevents the repetition of previous tokens through a penalty. This penalty is applied at most once per token. Note that, for decoder-only models like most LLMs, the considered tokens include the prompt.
In the original paper, the authors suggest the use of a penalty of around
1.2 to achieve a good balance between truthful generation and lack of repetition. To penalize and reduce
repetition, use penalty
values above 1.0, where a higher value penalizes more strongly. To reward and encourage
repetition, use penalty
values between 0.0 and 1.0, where a lower value rewards more strongly.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> # Initializing the model and tokenizer for it
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer(["I'm not going to"], return_tensors="pt")
>>> # This shows a normal generate without any specific parameters
>>> summary_ids = model.generate(**inputs)
>>> print(tokenizer.batch_decode(summary_ids, skip_special_tokens=True)[0])
I'm not going to be able to do that. I'm going to be able to do that
>>> # This generates a penalty for repeated tokens
>>> penalized_ids = model.generate(**inputs, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(penalized_ids, skip_special_tokens=True)[0])
I'm not going to be able to do that. I'll just have to go out and play
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.SequenceBiasLogitsProcessor
< source >( sequence_bias: typing.List[typing.List[typing.Union[typing.List[int], float]]] )
Parameters
- sequence_bias (
List[List[Union[List[int], float]]]
) — List of lists that maps a sequence of tokens to its bias term (e.g.[[[10, 45], -2.0], [[64], -7.5]]
). Positive biases increase the odds of the sequence being selected, while negative biases do the opposite. If a sequence has a length of 1, its bias will always be applied. Otherwise, the bias will only be applied if the sequence in question is about to be completed (in the token selection step after this processor is applied).
LogitsProcessor that applies an additive bias on sequences. The bias is applied to the last token of a sequence when the next generated token can complete it. Consequently, to take the most of biasing sequences with more than one token, consider using beam methods (to gracefully work around partially completed sequences that have a negative bias) and applying the bias to their prefixes (to ensure the bias is applied earlier).
In order to get the token ids of the sequences that you want to bias, make sure to set add_prefix_space=True
when
initializing the tokenizer, and use tokenizer(bad_words, add_special_tokens=False).input_ids
. The
add_prefix_space
argument is only supported for some slow tokenizers, as fast tokenizers’ prefixing behaviours
come from pre tokenizers
. Read more here.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> inputs = tokenizer(["The full name of Donald is Donald"], return_tensors="pt")
>>> summary_ids = model.generate(inputs["input_ids"], max_new_tokens=4)
>>> print(tokenizer.batch_decode(summary_ids, skip_special_tokens=True)[0])
The full name of Donald is Donald J. Trump Jr
>>> # Now let's control generation through a bias. Please note that the tokenizer is initialized differently!
>>> tokenizer_with_prefix_space = AutoTokenizer.from_pretrained("openai-community/gpt2", add_prefix_space=True)
>>> def get_tokens(word):
... return tokenizer_with_prefix_space([word], add_special_tokens=False).input_ids[0]
>>> # If we add a negative bias without beam search, it may become "stuck" in a prefix without good continuations
>>> sequence_bias = [get_tokens("Trump"), -10.0]
>>> biased_ids = model.generate(inputs["input_ids"], max_new_tokens=4, sequence_bias=sequence_bias)
>>> print(tokenizer.batch_decode(biased_ids, skip_special_tokens=True)[0])
The full name of Donald is Donald J. Donald,
>>> biased_ids = model.generate(inputs["input_ids"], max_new_tokens=4, num_beams=4, sequence_bias=sequence_bias)
>>> print(tokenizer.batch_decode(biased_ids, skip_special_tokens=True)[0])
The full name of Donald is Donald Rumsfeld,
>>> # We can also add a positive bias to nudge the model towards specific tokens or continuations
>>> sequence_bias = [get_tokens("Donald Duck"), 10.0]
>>> biased_ids = model.generate(inputs["input_ids"], max_new_tokens=4, num_beams=4, sequence_bias=sequence_bias)
>>> print(tokenizer.batch_decode(biased_ids, skip_special_tokens=True)[0])
The full name of Donald is Donald Duck.
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.SuppressTokensAtBeginLogitsProcessor
< source >( begin_suppress_tokens begin_index device: str = 'cpu' )
SuppressTokensAtBeginLogitsProcessor supresses a list of tokens as soon as the generate
function starts
generating using begin_index
tokens. This should ensure that the tokens defined by begin_suppress_tokens
are
not generated at the beginning. Originally created for
Whisper.
Examples:
>>> from transformers import AutoProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> processor = AutoProcessor.from_pretrained("openai/whisper-tiny.en")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en")
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> inputs = processor(ds[0]["audio"]["array"], return_tensors="pt")
>>> # Whisper has `begin_suppress_tokens` set by default (= `[220, 50256]`). 50256 is the EOS token, so this means
>>> # it can't generate and EOS token in the first iteration, but it can in the others.
>>> outputs = model.generate(**inputs, return_dict_in_generate=True, output_scores=True)
>>> print(outputs.scores[0][0, 50256])
tensor(-inf)
>>> print(outputs.scores[-1][0, 50256]) # in other places we can see some probability mass for EOS
tensor(29.9010)
>>> # If we disable `begin_suppress_tokens`, we can generate EOS in the first iteration.
>>> outputs = model.generate(
... **inputs, return_dict_in_generate=True, output_scores=True, begin_suppress_tokens=None
... )
>>> print(outputs.scores[0][0, 50256])
tensor(11.2027)
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
This processor can be used to suppress a list of tokens. The processor will set their log probs to -inf
so
that they are not generated. Originally created for
Whisper.
Examples:
>>> from transformers import AutoProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset
>>> processor = AutoProcessor.from_pretrained("openai/whisper-tiny.en")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en")
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> inputs = processor(ds[0]["audio"]["array"], return_tensors="pt")
>>> # Whisper has a long list of suppressed tokens. For instance, in this case, the token 1 is suppressed by default.
>>> outputs = model.generate(**inputs, return_dict_in_generate=True, output_scores=True)
>>> print(outputs.scores[1][0, 1]) # 1 (and not 0) is the first freely generated token
tensor(-inf)
>>> # If we disable `suppress_tokens`, we can generate it.
>>> outputs = model.generate(**inputs, return_dict_in_generate=True, output_scores=True, suppress_tokens=None)
>>> print(outputs.scores[1][0, 1])
tensor(6.0678)
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.SynthIDTextWatermarkLogitsProcessor
< source >( ngram_len: int keys: typing.List[int] sampling_table_size: int sampling_table_seed: int context_history_size: int device: device skip_first_ngram_calls: bool = False debug_mode: bool = False )
Parameters
- ngram_len (
int
) — Ngram length. - keys (
List[int]
) — A sequence of watermarking keys, one for each depth. - sampling_table_size (
int
) — Size of the sampling table. - sampling_table_seed (
int
) — Random seed to generate the sampling table. - context_history_size (
int
) — Size of the tensor to keep track of seen contexts. - device (
torch.device
) — Device to use. - skip_first_ngram_calls (
bool
, optional, defaults toFalse
) — Whether to skip first ngram calls. - debug_mode (
bool
, optional, optional, defaults toFalse
) — Logits are modified to uniform one got before watermarking modification is applied. This is to test the implementation.
Logits processor that implements watermarking techniques for text generation models. This class facilitates the application of SynthID text watermarking, a method for embedding imperceptible signals into generated text to aid in detecting synthetic content. It operates by subtly manipulating the probabilities of token selection during text generation in a manner that can be reliably recovered later for verification.
Key Features:
State Management: Maintains internal state to track token sequences and generate watermarking keys dynamically.
Key Generation: Computes hashes based on token sequences and watermarking parameters to create unique keys for each position.
G-Value Sampling: Employs a pre-computed sampling table to sample watermarking values (g-values) based on the generated keys.
Score Adjustment: Applies calculated g-values to modify token probabilities during generation, embedding the watermark.
Context Repetition Handling: Incorporates logic to avoid watermarking tokens in repeated contexts, preserving naturalness.
EOS Token Masking: Supports masking end-of-sentence tokens to prevent their inclusion in watermarking calculations.
Utility Functions: Provides functions to compute g-values directly, check for context repetition, create EOS token masks, and estimate expected mean g-values.
Refer to paper url: https://www.nature.com/articles/s41586-024-08025-4 for more details around this.
Examples:
>>> from transformers import AutoModelForCausalLM, AutoTokenizer, SynthIDTextWatermarkingConfig
>>> tokenizer = AutoTokenizer.from_pretrained('google/gemma-2-2b', padding_side="left")
>>> model = AutoModelForCausalLM.from_pretrained('google/gemma-2-2b')
>>> # SynthID Text configuration
>>> watermarking_config = SynthIDTextWatermarkingConfig(
... keys=[654, 400, 836, 123, 340, 443, 597, 160, 57],
... ngram_len=5,
... )
>>> # Generation with watermarking
>>> tokenized_prompts = tokenizer(["Once upon a time, "], return_tensors="pt", padding=True)
>>> output_sequences = model.generate(
... **tokenized_prompts, watermarking_config=watermarking_config, do_sample=True, max_new_tokens=10
... )
>>> watermarked_text = tokenizer.batch_decode(output_sequences, skip_special_tokens=True)
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.TemperatureLogitsWarper
< source >( temperature: float )
LogitsProcessor for temperature (exponential scaling output probability distribution), which effectively means that it can control the randomness of the predicted tokens. Often used together with TopPLogitsWarper and TopKLogitsWarper.
Make sure that do_sample=True
is included in the generate
arguments otherwise the temperature value won’t have
any effect.
Examples:
>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> set_seed(0) # for reproducibility
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> model.config.pad_token_id = model.config.eos_token_id
>>> inputs = tokenizer(["Hugging Face Company is"], return_tensors="pt")
>>> # With temperature=1.0, the default, we consistently get random outputs due to random sampling.
>>> generate_kwargs = {"max_new_tokens": 10, "do_sample": True, "temperature": 1.0, "num_return_sequences": 2}
>>> outputs = model.generate(**inputs, **generate_kwargs)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
['Hugging Face Company is one of these companies that is going to take a',
"Hugging Face Company is a brand created by Brian A. O'Neil"]
>>> # However, with temperature close to 0, it approximates greedy decoding strategies (invariant)
>>> generate_kwargs["temperature"] = 0.0001
>>> outputs = model.generate(**inputs, **generate_kwargs)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
['Hugging Face Company is a company that has been around for over 20 years',
'Hugging Face Company is a company that has been around for over 20 years']
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
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 -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.
LogitsProcessor that performs top-k, i.e. restricting to the k highest probability elements. Often used together with TemperatureLogitsWarper and TopPLogitsWarper.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> set_seed(1)
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer("A sequence: A, B, C, D", return_tensors="pt")
>>> # With sampling, the output is unexpected -- sometimes too unexpected.
>>> outputs = model.generate(**inputs, do_sample=True)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: A, B, C, D, E — S — O, P — R
>>> # With `top_k` sampling, the output gets restricted the k most likely tokens.
>>> # Pro tip: In practice, LLMs use `top_k` in the 5-50 range.
>>> outputs = model.generate(**inputs, do_sample=True, top_k=2)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: A, B, C, D, E, F, G, H, I
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
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 smallest set of most probable tokens with probabilities that add up totop_p
or higher are kept for generation. - filter_value (
float
, optional, defaults to -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.
LogitsProcessor that performs top-p, i.e. restricting to top tokens summing to prob_cut_off <= prob_cut_off. Often used together with TemperatureLogitsWarper and TopKLogitsWarper.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> set_seed(1)
>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
>>> inputs = tokenizer("A sequence: 1, 2", return_tensors="pt")
>>> # With sampling, the output is unexpected -- sometimes too unexpected.
>>> outputs = model.generate(**inputs, do_sample=True)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3 | < 4 (left-hand pointer) ;
<BLANKLINE>
<BLANKLINE>
>>> # With `top_p` sampling, the output gets restricted to high-probability tokens.
>>> # Pro tip: In practice, LLMs use `top_p` in the 0.9-0.95 range.
>>> outputs = model.generate(**inputs, do_sample=True, top_p=0.1)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3, 4, 5, 6, 7, 8, 9
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.TypicalLogitsWarper
< source >( mass: float = 0.9 filter_value: float = -inf min_tokens_to_keep: int = 1 )
Parameters
- mass (
float
, optional, defaults to 0.9) — Value of typical_p between 0 and 1 inclusive, defaults to 0.9. - filter_value (
float
, optional, defaults to -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.
LogitsProcessor that performs typical decoding. Inspired on how humans use language, it prioritizes tokens whose log probability is close to the entropy of the token probability distribution. This means that the most likely tokens may be discarded in the process.
See Typical Decoding for Natural Language Generation for more information.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-560m")
>>> tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-560m")
>>> inputs = tokenizer("1, 2, 3", return_tensors="pt")
>>> # We can see that greedy decoding produces a sequence of numbers
>>> outputs = model.generate(**inputs)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
>>> # For this particular seed, we can see that sampling produces nearly the same low-information (= low entropy)
>>> # sequence
>>> set_seed(18)
>>> outputs = model.generate(**inputs, do_sample=True)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
1, 2, 3, 4, 5, 6, 7, 8, 9 and 10
>>> # With `typical_p` set, the most obvious sequence is no longer produced, which may be good for your problem
>>> set_seed(18)
>>> outputs = model.generate(
... **inputs, do_sample=True, typical_p=0.1, return_dict_in_generate=True, output_scores=True
... )
>>> print(tokenizer.batch_decode(outputs.sequences, skip_special_tokens=True)[0])
1, 2, 3 and 5
>>> # We can see that the token corresponding to "4" (token 934) in the second position, the most likely token
>>> # as seen with greedy decoding, was entirely blocked out
>>> print(outputs.scores[1][0, 934])
tensor(-inf)
__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. 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
Returns
torch.FloatTensor
of shape (batch_size, config.vocab_size)
The processed prediction scores.
class transformers.UnbatchedClassifierFreeGuidanceLogitsProcessor
< source >( guidance_scale: float model unconditional_ids: typing.Optional[torch.LongTensor] = None unconditional_attention_mask: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = True )
Parameters
- guidance_scale (
float
) — The guidance scale for classifier free guidance (CFG). CFG is enabled by settingguidance_scale != 1
. Higher guidance scale encourages the model to generate samples that are more closely linked to the input prompt, usually at the expense of poorer quality. A value smaller than 1 has the opposite effect, while making the negative prompt provided with negative_prompt_ids (if any) act as a positive prompt. - model (
PreTrainedModel
) — The model computing the unconditional scores. Supposedly the same as the one computing the conditional scores. Both models must use the same tokenizer. - unconditional_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of input sequence tokens in the vocabulary for the unconditional branch. If unset, will default to the last token of the prompt. - unconditional_attention_mask (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Attention mask for unconditional_ids. - use_cache (
bool
, optional, defaults toTrue
) — Whether to cache key/values during the negative prompt forward pass.
Logits processor for Classifier-Free Guidance (CFG). The processors computes a weighted average across scores
from prompt conditional and prompt unconditional (or negative) logits, parameterized by the guidance_scale
.
The unconditional scores are computed internally by prompting model
with the unconditional_ids
branch.
See the paper for more information.
Examples:
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> inputs = tokenizer(["Today, a dragon flew over Paris, France,"], return_tensors="pt")
>>> out = model.generate(inputs["input_ids"], guidance_scale=1.5)
>>> tokenizer.batch_decode(out, skip_special_tokens=True)[0]
'Today, a dragon flew over Paris, France, killing at least 50 people and injuring more than 100'
>>> # with a negative prompt
>>> neg_inputs = tokenizer(["A very happy event happened,"], return_tensors="pt")
>>> out = model.generate(inputs["input_ids"], guidance_scale=2, negative_prompt_ids=neg_inputs["input_ids"])
>>> tokenizer.batch_decode(out, skip_special_tokens=True)[0]
'Today, a dragon flew over Paris, France, killing at least 130 people. French media reported that'
>>> # with a positive prompt
>>> neg_inputs = tokenizer(["A very happy event happened,"], return_tensors="pt")
>>> out = model.generate(inputs["input_ids"], guidance_scale=0, negative_prompt_ids=neg_inputs["input_ids"])
>>> tokenizer.batch_decode(out, skip_special_tokens=True)[0]
"Today, a dragon flew over Paris, France, and I'm very happy to be here. I"
class transformers.WhisperTimeStampLogitsProcessor
< source >( generate_config begin_index: typing.Optional[int] = None _detect_timestamp_from_logprob: typing.Optional[bool] = None )
Parameters
- generate_config (
GenerateConfig
) — The generate config used to generate the output. The following parameters are required: eos_token_id (int
, optional, defaults to 50257): The id of the end-of-sequence token. no_timestamps_token_id (int
, optional, defaults to 50363): The id of the"<|notimestamps|>"
token. max_initial_timestamp_index (int
, optional, defaults to 1): Used to set the maximum value of the initial timestamp. This is used to prevent the model from predicting timestamps that are too far in the future. - begin_index (
Optional
, optional) — Token index of the first token that is generated by the model. - _detect_timestamp_from_logprob (
bool
, optional) — Whether timestamps can be predicted from logprobs over all timestamps.
LogitsProcessor that modifies the logits for the generation of timestamps in the transcription. When the input tokens are at a specific threshold, the processor sets the scores to negative infinity. The processor makes sure that timestamp tokens appear in pairs, by masking out the logits that would break this pairing pattern. This is done to maintain the consistency and structure of generated timestamps. It also ensures that when the predicted probability of sampling any of the timestamp token is greater than any individual non-timestamp token, those non-timestamp logits are set to negative infinity. This is done to ensure the generation of timestamps over other potential tokens.
See the paper for more information.
Examples:
>>> import torch
>>> from transformers import AutoProcessor, WhisperForConditionalGeneration, GenerationConfig
>>> from datasets import load_dataset
>>> processor = AutoProcessor.from_pretrained("openai/whisper-tiny.en")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en")
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> inputs = processor(ds[3]["audio"]["array"], return_tensors="pt")
>>> input_features = inputs.input_features
>>> #Displaying timestamps
>>> generated_ids = model.generate(inputs=input_features, return_timestamps=True)
>>> transcription = processor.batch_decode(generated_ids, decode_with_timestamps=True)[0]
>>> print("Transcription:", transcription)
Transcription: <|startoftranscript|><|0.00|> He has grave doubts whether Sir Frederick Layton's work is really Greek after all, and can<|6.44|><|6.44|> discover in it but little of rocky Ithaca.<|9.44|><|endoftext|>
>>> #No timestamps & change EOS:
>>> #This allows the user to select a specific token to terminate the sequen