Transformers documentation

Generation

Transformers

You are viewing v4.38.2 version. A newer version v4.46.3 is available.

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Generation

Each framework has a generate method for text generation implemented in their respective GenerationMixin class:

PyTorch generate() is implemented in GenerationMixin.
TensorFlow generate() is implemented in TFGenerationMixin.
Flax/JAX generate() is implemented in FlaxGenerationMixin.

Regardless of your framework of choice, you can parameterize the generate method with a GenerationConfig class instance. Please refer to this class for the complete list of generation parameters, which control the behavior of the generation method.

To learn how to inspect a model’s generation configuration, what are the defaults, how to change the parameters ad hoc, and how to create and save a customized generation configuration, refer to the text generation strategies guide. The guide also explains how to use related features, like token streaming.

GenerationConfig

class transformers.GenerationConfig

( **kwargs )

Parameters that control the length of the output

max_length (int, optional, defaults to 20) — The maximum length the generated tokens can have. Corresponds to the length of the input prompt + max_new_tokens. Its effect is overridden by max_new_tokens, if also set.
max_new_tokens (int, optional) — The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt.
min_length (int, optional, defaults to 0) — The minimum length of the sequence to be generated. Corresponds to the length of the input prompt + min_new_tokens. Its effect is overridden by min_new_tokens, if also set.
min_new_tokens (int, optional) — The minimum numbers of tokens to generate, ignoring the number of tokens in the prompt.
early_stopping (bool or str, optional, defaults to False) — Controls the stopping condition for beam-based methods, like beam-search. It accepts the following values: True, where the generation stops as soon as there are num_beams complete candidates; False, where an heuristic is applied and the generation stops when is it very unlikely to find better candidates; "never", where the beam search procedure only stops when there cannot be better candidates (canonical beam search algorithm).
max_time(float, optional) — The maximum amount of time you allow the computation to run for in seconds. generation will still finish the current pass after allocated time has been passed.

Parameters that control the generation strategy used

do_sample (bool, optional, defaults to False) — Whether or not to use sampling ; use greedy decoding otherwise.
num_beams (int, optional, defaults to 1) — Number of beams for beam search. 1 means no beam search.
num_beam_groups (int, optional, defaults to 1) — Number of groups to divide num_beams into in order to ensure diversity among different groups of beams. this paper for more details.
penalty_alpha (float, optional) — The values balance the model confidence and the degeneration penalty in contrastive search decoding.
use_cache (bool, optional, defaults to True) — Whether or not the model should use the past last key/values attentions (if applicable to the model) to speed up decoding.

Parameters for manipulation of the model output logits

temperature (float, optional, defaults to 1.0) — The value used to modulate the next token probabilities.
top_k (int, optional, defaults to 50) — The number of highest probability vocabulary tokens to keep for top-k-filtering.
top_p (float, optional, defaults to 1.0) — If set to float < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.
typical_p (float, optional, defaults to 1.0) — Local typicality measures how similar the conditional probability of predicting a target token next is to the expected conditional probability of predicting a random token next, given the partial text already generated. If set to float < 1, the smallest set of the most locally typical tokens with probabilities that add up to typical_p or higher are kept for generation. See this paper for more details.
epsilon_cutoff (float, optional, defaults to 0.0) — If set to float strictly between 0 and 1, only tokens with a conditional probability greater than epsilon_cutoff will be sampled. In the paper, suggested values range from 3e-4 to 9e-4, depending on the size of the model. See Truncation Sampling as Language Model Desmoothing for more details.
eta_cutoff (float, optional, defaults to 0.0) — Eta sampling is a hybrid of locally typical sampling and epsilon sampling. If set to float strictly between 0 and 1, a token is only considered if it is greater than either eta_cutoff or sqrt(eta_cutoff) * exp(-entropy(softmax(next_token_logits))). The latter term is intuitively the expected next token probability, scaled by sqrt(eta_cutoff). In the paper, suggested values range from 3e-4 to 2e-3, depending on the size of the model. See Truncation Sampling as Language Model Desmoothing for more details.
diversity_penalty (float, optional, defaults to 0.0) — This value is subtracted from a beam’s score if it generates a token same as any beam from other group at a particular time. Note that diversity_penalty is only effective if group beam search is enabled.
repetition_penalty (float, optional, defaults to 1.0) — The parameter for repetition penalty. 1.0 means no penalty. See this paper for more details.
encoder_repetition_penalty (float, optional, defaults to 1.0) — The paramater for encoder_repetition_penalty. An exponential penalty on sequences that are not in the original input. 1.0 means no penalty.
length_penalty (float, optional, defaults to 1.0) — Exponential penalty to the length that is used with beam-based generation. It is applied as an exponent to the sequence length, which in turn is used to divide the score of the sequence. Since the score is the log likelihood of the sequence (i.e. negative), length_penalty > 0.0 promotes longer sequences, while length_penalty < 0.0 encourages shorter sequences.
no_repeat_ngram_size (int, optional, defaults to 0) — If set to int > 0, all ngrams of that size can only occur once.
bad_words_ids(List[List[int]], optional) — List of list of token ids that are not allowed to be generated. Check NoBadWordsLogitsProcessor for further documentation and examples.
force_words_ids(List[List[int]] or List[List[List[int]]], optional) — List of token ids that must be generated. If given a List[List[int]], this is treated as a simple list of words that must be included, the opposite to bad_words_ids. If given List[List[List[int]]], this triggers a disjunctive constraint, where one can allow different forms of each word.
renormalize_logits (bool, optional, defaults to False) — Whether to renormalize the logits after applying all the logits processors or warpers (including the custom ones). It’s highly recommended to set this flag to True as the search algorithms suppose the score logits are normalized but some logit processors or warpers break the normalization.
constraints (List[Constraint], optional) — Custom constraints that can be added to the generation to ensure that the output will contain the use of certain tokens as defined by Constraint objects, in the most sensible way possible.
forced_bos_token_id (int, optional, defaults to model.config.forced_bos_token_id) — The id of the token to force as the first generated token after the decoder_start_token_id. Useful for multilingual models like mBART where the first generated token needs to be the target language token.
forced_eos_token_id (Union[int, List[int]], optional, defaults to model.config.forced_eos_token_id) — The id of the token to force as the last generated token when max_length is reached. Optionally, use a list to set multiple end-of-sequence tokens.
remove_invalid_values (bool, optional, defaults to model.config.remove_invalid_values) — Whether to remove possible nan and inf outputs of the model to prevent the generation method to crash. Note that using remove_invalid_values can slow down generation.
exponential_decay_length_penalty (tuple(int, float), optional) — This Tuple adds an exponentially increasing length penalty, after a certain amount of tokens have been generated. The tuple shall consist of: (start_index, decay_factor) where start_index indicates where penalty starts and decay_factor represents the factor of exponential decay
suppress_tokens (List[int], optional) — A list of tokens that will be suppressed at generation. The SupressTokens logit processor will set their log probs to -inf so that they are not sampled.
begin_suppress_tokens (List[int], optional) — A list of tokens that will be suppressed at the beginning of the generation. The SupressBeginTokens logit processor will set their log probs to -inf so that they are not sampled.
forced_decoder_ids (List[List[int]], optional) — A list of pairs of integers which indicates a mapping from generation indices to token indices that will be forced before sampling. For example, [[1, 123]] means the second generated token will always be a token of index 123.
sequence_bias (Dict[Tuple[int], float], optional)) — Dictionary that maps a sequence of tokens to its bias term. Positive biases increase the odds of the sequence being selected, while negative biases do the opposite. Check SequenceBiasLogitsProcessor for further documentation and examples.
guidance_scale (float, optional) — The guidance scale for classifier free guidance (CFG). CFG is enabled by setting guidance_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.
low_memory (bool, optional) — Switch to sequential beam search and sequential topk for contrastive search to reduce peak memory. Used with beam search and contrastive search.

Parameters that define the output variables of `generate`

num_return_sequences(int, optional, defaults to 1) — The number of independently computed returned sequences for each element in the batch.
output_attentions (bool, optional, defaults to False) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more details.
output_hidden_states (bool, optional, defaults to False) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more details.
output_scores (bool, optional, defaults to False) — Whether or not to return the prediction scores. See scores under returned tensors for more details.
output_logits (bool, optional) — Whether or not to return the unprocessed prediction logit scores. See logits under returned tensors for more details.
return_dict_in_generate (bool, optional, defaults to False) — Whether or not to return a ModelOutput instead of a plain tuple.

Special tokens that can be used at generation time

pad_token_id (int, optional) — The id of the padding token.
bos_token_id (int, optional) — The id of the beginning-of-sequence token.
eos_token_id (Union[int, List[int]], optional) — The id of the end-of-sequence token. Optionally, use a list to set multiple end-of-sequence tokens.

Generation parameters exclusive to encoder-decoder models

encoder_no_repeat_ngram_size (int, optional, defaults to 0) — If set to int > 0, all ngrams of that size that occur in the encoder_input_ids cannot occur in the decoder_input_ids.
decoder_start_token_id (Union[int, List[int]], optional) — If an encoder-decoder model starts decoding with a different token than bos, the id of that token or a list of length batch_size. Indicating a list enables different start ids for each element in the batch (e.g. multilingual models with different target languages in one batch)

Generation parameters exclusive to [assistant generation](https

num_assistant_tokens (int, optional, defaults to 5) — Defines the number of speculative tokens that shall be generated by the assistant model before being checked by the target model at each iteration. Higher values for num_assistant_tokens make the generation more speculative : If the assistant model is performant larger speed-ups can be reached, if the assistant model requires lots of corrections, lower speed-ups are reached.
num_assistant_tokens_schedule (str, optional, defaults to "heuristic") — Defines the schedule at which max assistant tokens shall be changed during inference.
- "heuristic": When all speculative tokens are correct, increase num_assistant_tokens by 2 else reduce by 1. num_assistant_tokens value is persistent over multiple generation calls with the same assistant model.
- "heuristic_transient": Same as "heuristic" but num_assistant_tokens is reset to its initial value after each generation call.
- "constant": num_assistant_tokens stays unchanged during generation

Parameters specific to the caching mechanism

cache_implementation (str, optional, default to None) — Cache class that should be used when generating.

Wild card

Class that holds a configuration for a generation task. A generate call supports the following generation methods for text-decoder, text-to-text, speech-to-text, and vision-to-text models:

greedy decoding by calling greedy_search() if num_beams=1 and do_sample=False
contrastive search by calling contrastive_search() if penalty_alpha>0. and top_k>1
multinomial sampling by calling sample() if num_beams=1 and do_sample=True
beam-search decoding by calling beam_search() if num_beams>1 and do_sample=False
beam-search multinomial sampling by calling beam_sample() if num_beams>1 and do_sample=True
diverse beam-search decoding by calling group_beam_search(), if num_beams>1 and num_beam_groups>1
constrained beam-search decoding by calling constrained_beam_search(), if constraints!=None or force_words_ids!=None
assisted decoding by calling assisted_decoding(), if assistant_model is passed to .generate()

You do not need to call any of the above methods directly. Pass custom parameter values to ‘.generate()‘. To learn more about decoding strategies refer to the text generation strategies guide.

A large number of these flags control the logits or the stopping criteria of the generation. Make sure you check the generate-related classes for a full description of the possible manipulations, as well as examples of their usage.

from_pretrained

( pretrained_model_name: Union config_file_name: Union = None cache_dir: Union = None force_download: bool = False local_files_only: bool = False token: Union = None revision: str = 'main' **kwargs ) → GenerationConfig

Parameters

pretrained_model_name (str or os.PathLike) — This can be either:
- a string, the model id of a pretrained model configuration hosted inside a model repo on huggingface.co.
- a path to a directory containing a configuration file saved using the save_pretrained() method, e.g., ./my_model_directory/.
config_file_name (str or os.PathLike, optional, defaults to "generation_config.json") — Name of the generation configuration JSON file to be loaded from pretrained_model_name.
cache_dir (str or os.PathLike, optional) — Path to a directory in which a downloaded pretrained model configuration should be cached if the standard cache should not be used.
force_download (bool, optional, defaults to False) — Whether or not to force to (re-)download the configuration files and override the cached versions if they exist.
resume_download (bool, optional, defaults to False) — Whether or not to delete incompletely received file. Attempts to resume the download if such a file exists.
proxies (Dict[str, str], optional) — A dictionary of proxy servers to use by protocol or endpoint, e.g., {'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}. The proxies are used on each request.
token (str or bool, optional) — The token to use as HTTP bearer authorization for remote files. If True, or not specified, will use the token generated when running huggingface-cli login (stored in ~/.huggingface).
revision (str, optional, defaults to "main") — The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so revision can be any identifier allowed by git.

To test a pull request you made on the Hub, you can pass `revision=“refs/pr/“.
return_unused_kwargs (bool, optional, defaults to False) — If False, then this function returns just the final configuration object.

If True, then this functions returns a Tuple(config, unused_kwargs) where unused_kwargs is a dictionary consisting of the key/value pairs whose keys are not configuration attributes: i.e., the part of kwargs which has not been used to update config and is otherwise ignored.
subfolder (str, optional, defaults to "") — In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can specify the folder name here.
kwargs (Dict[str, Any], optional) — The values in kwargs of any keys which are configuration attributes will be used to override the loaded values. Behavior concerning key/value pairs whose keys are not configuration attributes is controlled by the return_unused_kwargs keyword parameter.

Returns

GenerationConfig

The configuration object instantiated from this pretrained model.

Instantiate a GenerationConfig from a generation configuration file.

Examples:

>>> from transformers import GenerationConfig

>>> # Download configuration from huggingface.co and cache.
>>> generation_config = GenerationConfig.from_pretrained("openai-community/gpt2")

>>> # E.g. config was saved using *save_pretrained('./test/saved_model/')*
>>> generation_config.save_pretrained("./test/saved_model/")
>>> generation_config = GenerationConfig.from_pretrained("./test/saved_model/")

>>> # You can also specify configuration names to your generation configuration file
>>> generation_config.save_pretrained("./test/saved_model/", config_file_name="my_configuration.json")
>>> generation_config = GenerationConfig.from_pretrained("./test/saved_model/", "my_configuration.json")

>>> # If you'd like to try a minor variation to an existing configuration, you can also pass generation
>>> # arguments to `.from_pretrained()`. Be mindful that typos and unused arguments will be ignored
>>> generation_config, unused_kwargs = GenerationConfig.from_pretrained(
...     "openai-community/gpt2", top_k=1, foo=False, do_sample=True, return_unused_kwargs=True
... )
>>> generation_config.top_k
1

>>> unused_kwargs
{'foo': False}

from_model_config

( model_config: PretrainedConfig ) → GenerationConfig

Parameters

model_config (PretrainedConfig) — The model config that will be used to instantiate the generation config.

Returns

GenerationConfig

The configuration object instantiated from those parameters.

Instantiates a GenerationConfig from a PretrainedConfig. This function is useful to convert legacy PretrainedConfig objects, which may contain generation parameters, into a stand-alone GenerationConfig.

save_pretrained

( save_directory: Union config_file_name: Union = None push_to_hub: bool = False **kwargs )

Parameters

save_directory (str or os.PathLike) — Directory where the configuration JSON file will be saved (will be created if it does not exist).
config_file_name (str or os.PathLike, optional, defaults to "generation_config.json") — Name of the generation configuration JSON file to be saved in save_directory.
push_to_hub (bool, optional, defaults to False) — Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with repo_id (will default to the name of save_directory in your namespace).
kwargs (Dict[str, Any], optional) — Additional key word arguments passed along to the push_to_hub() method.

Save a generation configuration object to the directory save_directory, so that it can be re-loaded using the from_pretrained() class method.

GenerationMixin

class transformers.GenerationMixin

( )

A class containing all functions for auto-regressive text generation, to be used as a mixin in PreTrainedModel.

The class exposes generate(), which can be used for:

greedy decoding by calling greedy_search() if num_beams=1 and do_sample=False
contrastive search by calling contrastive_search() if penalty_alpha>0 and top_k>1
multinomial sampling by calling sample() if num_beams=1 and do_sample=True
beam-search decoding by calling beam_search() if num_beams>1 and do_sample=False
beam-search multinomial sampling by calling beam_sample() if num_beams>1 and do_sample=True
diverse beam-search decoding by calling group_beam_search(), if num_beams>1 and num_beam_groups>1
constrained beam-search decoding by calling constrained_beam_search(), if constraints!=None or force_words_ids!=None

You do not need to call any of the above methods directly. Pass custom parameter values to ‘generate’ instead. To learn more about decoding strategies refer to the text generation strategies guide.

generate

( inputs: Optional = None generation_config: Optional = None logits_processor: Optional = None stopping_criteria: Optional = None prefix_allowed_tokens_fn: Optional = None synced_gpus: Optional = None assistant_model: Optional = None streamer: Optional = None negative_prompt_ids: Optional = None negative_prompt_attention_mask: Optional = None **kwargs ) → ModelOutput or torch.LongTensor

Parameters

inputs (torch.Tensor of varying shape depending on the modality, optional) — The sequence used as a prompt for the generation or as model inputs to the encoder. If None the method initializes it with bos_token_id and a batch size of 1. For decoder-only models inputs should of in the format of input_ids. For encoder-decoder models inputs can represent any of input_ids, input_values, input_features, or pixel_values.
generation_config (~generation.GenerationConfig, optional) — The generation configuration to be used as base parametrization for the generation call. **kwargs passed to generate matching the attributes of generation_config will override them. If generation_config is not provided, the default will be used, which had the following loading priority: 1) from the generation_config.json model file, if it exists; 2) from the model configuration. Please note that unspecified parameters will inherit GenerationConfig’s default values, whose documentation should be checked to parameterize generation.
logits_processor (LogitsProcessorList, optional) — Custom logits processors that complement the default logits processors built from arguments and generation config. If a logit processor is passed that is already created with the arguments or a generation config an error is thrown. This feature is intended for advanced users.
stopping_criteria (StoppingCriteriaList, optional) — Custom stopping criteria that complement the default stopping criteria built from arguments and a generation config. If a stopping criteria is passed that is already created with the arguments or a generation config an error is thrown. If your stopping criteria depends on the scores input, make sure you pass return_dict_in_generate=True, output_scores=True to generate. This feature is intended for advanced users.
prefix_allowed_tokens_fn (Callable[[int, torch.Tensor], List[int]], optional) — If provided, this function constraints the beam search to allowed tokens only at each step. If not provided no constraint is applied. This function takes 2 arguments: the batch ID batch_id and input_ids. It has to return a list with the allowed tokens for the next generation step conditioned on the batch ID batch_id and the previously generated tokens inputs_ids. This argument is useful for constrained generation conditioned on the prefix, as described in Autoregressive Entity Retrieval.
synced_gpus (bool, optional) — Whether to continue running the while loop until max_length. Unless overridden this flag will be set to True under DeepSpeed ZeRO Stage 3 multiple GPUs environment to avoid hanging if one GPU finished generating before other GPUs. Otherwise it’ll be set to False.
assistant_model (PreTrainedModel, optional) — An assistant model that can be used to accelerate generation. The assistant model must have the exact same tokenizer. The acceleration is achieved when forecasting candidate tokens with the assistent model is much faster than running generation with the model you’re calling generate from. As such, the assistant model should be much smaller.
streamer (BaseStreamer, optional) — Streamer object that will be used to stream the generated sequences. Generated tokens are passed through streamer.put(token_ids) and the streamer is responsible for any further processing.
negative_prompt_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — The negative prompt needed for some processors such as CFG. The batch size must match the input batch size. This is an experimental feature, subject to breaking API changes in future versions.
negative_prompt_attention_mask (torch.LongTensor of shape (batch_size, sequence_length), optional) — Attention_mask for negative_prompt_ids.
kwargs (Dict[str, Any], optional) — Ad hoc parametrization of generate_config and/or additional model-specific kwargs that will be forwarded to the forward function of the model. If the model is an encoder-decoder model, encoder specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with decoder_.

Returns

ModelOutput or torch.LongTensor

A ModelOutput (if return_dict_in_generate=True or when config.return_dict_in_generate=True) or a torch.FloatTensor.

If the model is not an encoder-decoder model (model.config.is_encoder_decoder=False), the possible ModelOutput types are:

If the model is an encoder-decoder model (model.config.is_encoder_decoder=True), the possible ModelOutput types are:

Generates sequences of token ids for models with a language modeling head.

Most generation-controlling parameters are set in generation_config which, if not passed, will be set to the model’s default generation configuration. You can override any generation_config by passing the corresponding parameters to generate(), e.g. .generate(inputs, num_beams=4, do_sample=True).

For an overview of generation strategies and code examples, check out the following guide.

compute_transition_scores

( sequences: Tensor scores: Tuple beam_indices: Optional = None normalize_logits: bool = False ) → torch.Tensor

Parameters

sequences (torch.LongTensor) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
scores (tuple(torch.FloatTensor)) — 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 Tuple of torch.FloatTensor with up to max_new_tokens elements (one element for each generated token), with each tensor of shape (batch_size*num_beams, config.vocab_size).
beam_indices (torch.LongTensor, optional) — Beam indices of generated token id at each generation step. torch.LongTensor of shape (batch_size*num_return_sequences, sequence_length). Only required if a num_beams>1 at generate-time.
normalize_logits (bool, optional, defaults to False) — Whether to normalize the logits (which, for legacy reasons, may be unnormalized).

Returns

torch.Tensor

A torch.Tensor of shape (batch_size*num_return_sequences, sequence_length) containing the transition scores (logits)

Computes the transition scores of sequences given the generation scores (and beam indices, if beam search was used). This is a convenient method to quicky obtain the scores of the selected tokens at generation time.

Examples:

>>> from transformers import GPT2Tokenizer, AutoModelForCausalLM
>>> import numpy as np

>>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> tokenizer.pad_token_id = tokenizer.eos_token_id
>>> inputs = tokenizer(["Today is"], return_tensors="pt")

>>> # Example 1: Print the scores for each token generated with Greedy Search
>>> outputs = model.generate(**inputs, max_new_tokens=5, return_dict_in_generate=True, output_scores=True)
>>> transition_scores = model.compute_transition_scores(
...     outputs.sequences, outputs.scores, normalize_logits=True
... )
>>> # input_length is the length of the input prompt for decoder-only models, like the GPT family, and 1 for
>>> # encoder-decoder models, like BART or T5.
>>> input_length = 1 if model.config.is_encoder_decoder else inputs.input_ids.shape[1]
>>> generated_tokens = outputs.sequences[:, input_length:]
>>> for tok, score in zip(generated_tokens[0], transition_scores[0]):
...     # | token | token string | log probability | probability
...     print(f"| {tok:5d} | {tokenizer.decode(tok):8s} | {score.numpy():.3f} | {np.exp(score.numpy()):.2%}")
|   262 |  the     | -1.414 | 24.33%
|  1110 |  day     | -2.609 | 7.36%
|   618 |  when    | -2.010 | 13.40%
|   356 |  we      | -1.859 | 15.58%
|   460 |  can     | -2.508 | 8.14%

>>> # Example 2: Reconstruct the sequence scores from Beam Search
>>> outputs = model.generate(
...     **inputs,
...     max_new_tokens=5,
...     num_beams=4,
...     num_return_sequences=4,
...     return_dict_in_generate=True,
...     output_scores=True,
... )
>>> transition_scores = model.compute_transition_scores(
...     outputs.sequences, outputs.scores, outputs.beam_indices, normalize_logits=False
... )
>>> # If you sum the generated tokens' scores and apply the length penalty, you'll get the sequence scores.
>>> # Tip 1: recomputing the scores is only guaranteed to match with `normalize_logits=False`. Depending on the
>>> # use case, you might want to recompute it with `normalize_logits=True`.
>>> # Tip 2: the output length does NOT include the input length
>>> output_length = np.sum(transition_scores.numpy() < 0, axis=1)
>>> length_penalty = model.generation_config.length_penalty
>>> reconstructed_scores = transition_scores.sum(axis=1) / (output_length**length_penalty)
>>> print(np.allclose(outputs.sequences_scores, reconstructed_scores))
True

greedy_search

( input_ids: LongTensor logits_processor: Optional = None stopping_criteria: Optional = None max_length: Optional = None pad_token_id: Optional = None eos_token_id: Union = None output_attentions: Optional = None output_hidden_states: Optional = None output_scores: Optional = None output_logits: Optional = None return_dict_in_generate: Optional = None synced_gpus: bool = False streamer: Optional = None **model_kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — The sequence used as a prompt for the generation.
logits_processor (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsProcessor used to modify the prediction scores of the language modeling head applied at each generation step.
stopping_criteria (StoppingCriteriaList, optional) — An instance of StoppingCriteriaList. List of instances of class derived from StoppingCriteria used to tell if the generation loop should stop.
max_length (int, optional, defaults to 20) — DEPRECATED. Use logits_processor or stopping_criteria directly to cap the number of generated tokens. The maximum length of the sequence to be generated.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (Union[int, List[int]], optional) — The id of the end-of-sequence token. Optionally, use a list to set multiple end-of-sequence tokens.
output_attentions (bool, optional, defaults to False) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more details.
output_hidden_states (bool, optional, defaults to False) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more details.
output_scores (bool, optional, defaults to False) — Whether or not to return the prediction scores. See scores under returned tensors for more details.
output_logits (bool, optional, defaults to False) — Whether or not to return the raw prediction logit scores. See logits under returned tensors for more details.
return_dict_in_generate (bool, optional, defaults to False) — Whether or not to return a ModelOutput instead of a plain tuple.
synced_gpus (bool, optional, defaults to False) — Whether to continue running the while loop until max_length (needed for ZeRO stage 3)
streamer (BaseStreamer, optional) — Streamer object that will be used to stream the generated sequences. Generated tokens are passed through streamer.put(token_ids) and the streamer is responsible for any further processing. model_kwargs — Additional model specific keyword arguments will be forwarded to the forward function of the model. If model is an encoder-decoder model the kwargs should include encoder_outputs.

Generates sequences of token ids for models with a language modeling head using greedy decoding and can be used for text-decoder, text-to-text, speech-to-text, and vision-to-text models.

In most cases, you do not need to call greedy_search() directly. Use generate() instead. For an overview of generation strategies and code examples, check the following guide.

Examples:

>>> from transformers import (
...     AutoTokenizer,
...     AutoModelForCausalLM,
...     LogitsProcessorList,
...     MinLengthLogitsProcessor,
...     StoppingCriteriaList,
...     MaxLengthCriteria,
... )

>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")

>>> # set pad_token_id to eos_token_id because GPT2 does not have a PAD token
>>> model.generation_config.pad_token_id = model.generation_config.eos_token_id

>>> input_prompt = "It might be possible to"
>>> input_ids = tokenizer(input_prompt, return_tensors="pt").input_ids

>>> # instantiate logits processors
>>> logits_processor = LogitsProcessorList(
...     [
...         MinLengthLogitsProcessor(10, eos_token_id=model.generation_config.eos_token_id),
...     ]
... )
>>> stopping_criteria = StoppingCriteriaList([MaxLengthCriteria(max_length=20)])

>>> outputs = model.greedy_search(
...     input_ids, logits_processor=logits_processor, stopping_criteria=stopping_criteria
... )

>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
["It might be possible to get a better understanding of the nature of the problem, but it's not"]

sample

( input_ids: LongTensor logits_processor: Optional = None stopping_criteria: Optional = None logits_warper: Optional = None max_length: Optional = None pad_token_id: Optional = None eos_token_id: Union = None output_attentions: Optional = None output_hidden_states: Optional = None output_scores: Optional = None output_logits: Optional = None return_dict_in_generate: Optional = None synced_gpus: bool = False streamer: Optional = None **model_kwargs ) → GenerateDecoderOnlyOutput, GenerateEncoderDecoderOutput or torch.LongTensor

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — The sequence used as a prompt for the generation.
logits_processor (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsProcessor used to modify the prediction scores of the language modeling head applied at each generation step.
stopping_criteria (StoppingCriteriaList, optional) — An instance of StoppingCriteriaList. List of instances of class derived from StoppingCriteria used to tell if the generation loop should stop.
logits_warper (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsWarper used to warp the prediction score distribution of the language modeling head applied before multinomial sampling at each generation step.
max_length (int, optional, defaults to 20) — DEPRECATED. Use logits_processor or stopping_criteria directly to cap the number of generated tokens. The maximum length of the sequence to be generated.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (Union[int, List[int]], optional) — The id of the end-of-sequence token. Optionally, use a list to set multiple end-of-sequence tokens.
output_attentions (bool, optional, defaults to False) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more details.
output_hidden_states (bool, optional, defaults to False) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more details.
output_scores (bool, optional, defaults to False) — Whether or not to return the prediction scores. See scores under returned tensors for more details.
output_logits (bool, optional, defaults to False) — Whether or not to return the raw prediction logit scores. See logits under returned tensors for more details.
return_dict_in_generate (bool, optional, defaults to False) — Whether or not to return a ModelOutput instead of a plain tuple.
synced_gpus (bool, optional, defaults to False) — Whether to continue running the while loop until max_length (needed for ZeRO stage 3)
streamer (BaseStreamer, optional) — Streamer object that will be used to stream the generated sequences. Generated tokens are passed through streamer.put(token_ids) and the streamer is responsible for any further processing. model_kwargs — Additional model specific kwargs will be forwarded to the forward function of the model. If model is an encoder-decoder model the kwargs should include encoder_outputs.

Returns

GenerateDecoderOnlyOutput, GenerateEncoderDecoderOutput or torch.LongTensor

A torch.LongTensor containing the generated tokens (default behaviour) or a GenerateDecoderOnlyOutput if model.config.is_encoder_decoder=False and return_dict_in_generate=True or a GenerateEncoderDecoderOutput if model.config.is_encoder_decoder=True.

Generates sequences of token ids for models with a language modeling head using multinomial sampling and can be used for text-decoder, text-to-text, speech-to-text, and vision-to-text models.

In most cases, you do not need to call sample() directly. Use generate() instead. For an overview of generation strategies and code examples, check the following guide.

Examples:

>>> from transformers import (
...     AutoTokenizer,
...     AutoModelForCausalLM,
...     LogitsProcessorList,
...     MinLengthLogitsProcessor,
...     TopKLogitsWarper,
...     TemperatureLogitsWarper,
...     StoppingCriteriaList,
...     MaxLengthCriteria,
... )
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")

>>> # set pad_token_id to eos_token_id because GPT2 does not have a EOS token
>>> model.config.pad_token_id = model.config.eos_token_id
>>> model.generation_config.pad_token_id = model.config.eos_token_id

>>> input_prompt = "Today is a beautiful day, and"
>>> input_ids = tokenizer(input_prompt, return_tensors="pt").input_ids

>>> # instantiate logits processors
>>> logits_processor = LogitsProcessorList(
...     [
...         MinLengthLogitsProcessor(15, eos_token_id=model.generation_config.eos_token_id),
...     ]
... )
>>> # instantiate logits processors
>>> logits_warper = LogitsProcessorList(
...     [
...         TopKLogitsWarper(50),
...         TemperatureLogitsWarper(0.7),
...     ]
... )

>>> stopping_criteria = StoppingCriteriaList([MaxLengthCriteria(max_length=20)])

>>> torch.manual_seed(0)
>>> outputs = model.sample(
...     input_ids,
...     logits_processor=logits_processor,
...     logits_warper=logits_warper,
...     stopping_criteria=stopping_criteria,
... )

>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Today is a beautiful day, and we must do everything possible to make it a day of celebration.']

beam_search

( input_ids: LongTensor beam_scorer: BeamScorer logits_processor: Optional = None stopping_criteria: Optional = None max_length: Optional = None pad_token_id: Optional = None eos_token_id: Union = None output_attentions: Optional = None output_hidden_states: Optional = None output_scores: Optional = None output_logits: Optional = None return_dict_in_generate: Optional = None synced_gpus: bool = False sequential: Optional = None **model_kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — The sequence used as a prompt for the generation.
beam_scorer (BeamScorer) — An derived instance of BeamScorer that defines how beam hypotheses are constructed, stored and sorted during generation. For more information, the documentation of BeamScorer should be read.
logits_processor (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsProcessor used to modify the prediction scores of the language modeling head applied at each generation step.
stopping_criteria (StoppingCriteriaList, optional) — An instance of StoppingCriteriaList. List of instances of class derived from StoppingCriteria used to tell if the generation loop should stop.
max_length (int, optional, defaults to 20) — DEPRECATED. Use logits_processor or stopping_criteria directly to cap the number of generated tokens. The maximum length of the sequence to be generated.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (Union[int, List[int]], optional) — The id of the end-of-sequence token. Optionally, use a list to set multiple end-of-sequence tokens.
output_attentions (bool, optional, defaults to False) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more details.
output_hidden_states (bool, optional, defaults to False) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more details.
output_logits (bool, optional, defaults to False) — Whether or not to return the raw prediction logit scores. See logits under returned tensors for more details.
output_scores (bool, optional, defaults to False) — Whether or not to return the prediction scores. See scores under returned tensors for more details.
return_dict_in_generate (bool, optional, defaults to False) — Whether or not to return a ModelOutput instead of a plain tuple.
synced_gpus (bool, optional, defaults to False) — Whether to continue running the while loop until max_length (needed for ZeRO stage 3)
sequential (bool, defaults to False) — By default, beam search has batch_size * num_beams as effective batch size (see beam_search() for more details). This flag will avoid parallelizing the beam search and will instead run beam search sequentially. model_kwargs — Additional model specific kwargs will be forwarded to the forward function of the model. If model is an encoder-decoder model the kwargs should include encoder_outputs.

Generates sequences of token ids for models with a language modeling head using beam search decoding and can be used for text-decoder, text-to-text, speech-to-text, and vision-to-text models.

In most cases, you do not need to call beam_search() directly. Use generate() instead. For an overview of generation strategies and code examples, check the following guide.

Examples:

>>> from transformers import (
...     AutoTokenizer,
...     AutoModelForSeq2SeqLM,
...     LogitsProcessorList,
...     MinLengthLogitsProcessor,
...     BeamSearchScorer,
... )
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-base")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("google-t5/t5-base")

>>> encoder_input_str = "translate English to German: How old are you?"
>>> encoder_input_ids = tokenizer(encoder_input_str, return_tensors="pt").input_ids


>>> # lets run beam search using 3 beams
>>> num_beams = 3
>>> # define decoder start token ids
>>> input_ids = torch.ones((num_beams, 1), device=model.device, dtype=torch.long)
>>> input_ids = input_ids * model.config.decoder_start_token_id

>>> # add encoder_outputs to model keyword arguments
>>> model_kwargs = {
...     "encoder_outputs": model.get_encoder()(
...         encoder_input_ids.repeat_interleave(num_beams, dim=0), return_dict=True
...     )
... }

>>> # instantiate beam scorer
>>> beam_scorer = BeamSearchScorer(
...     batch_size=1,
...     num_beams=num_beams,
...     device=model.device,
... )

>>> # instantiate logits processors
>>> logits_processor = LogitsProcessorList(
...     [
...         MinLengthLogitsProcessor(5, eos_token_id=model.config.eos_token_id),
...     ]
... )

>>> outputs = model.beam_search(input_ids, beam_scorer, logits_processor=logits_processor, **model_kwargs)

>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Wie alt bist du?']

beam_sample

( input_ids: LongTensor beam_scorer: BeamScorer logits_processor: Optional = None stopping_criteria: Optional = None logits_warper: Optional = None max_length: Optional = None pad_token_id: Optional = None eos_token_id: Union = None output_attentions: Optional = None output_hidden_states: Optional = None output_scores: Optional = None output_logits: Optional = None return_dict_in_generate: Optional = None synced_gpus: bool = False **model_kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — The sequence used as a prompt for the generation.
beam_scorer (BeamScorer) — A derived instance of BeamScorer that defines how beam hypotheses are constructed, stored and sorted during generation. For more information, the documentation of BeamScorer should be read.
logits_processor (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsProcessor used to modify the prediction scores of the language modeling head applied at each generation step.
stopping_criteria (StoppingCriteriaList, optional) — An instance of StoppingCriteriaList. List of instances of class derived from StoppingCriteria used to tell if the generation loop should stop.
logits_warper (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsWarper used to warp the prediction score distribution of the language modeling head applied before multinomial sampling at each generation step.
max_length (int, optional, defaults to 20) — DEPRECATED. Use logits_processor or stopping_criteria directly to cap the number of generated tokens. The maximum length of the sequence to be generated.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (Union[int, List[int]], optional) — The id of the end-of-sequence token. Optionally, use a list to set multiple end-of-sequence tokens.
output_attentions (bool, optional, defaults to False) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more details.
output_hidden_states (bool, optional, defaults to False) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more details.
output_scores (bool, optional, defaults to False) — Whether or not to return the prediction scores. See scores under returned tensors for more details.
output_logits (bool, optional, defaults to False) — Whether or not to return the raw prediction logit scores. See logits under returned tensors for more details.
return_dict_in_generate (bool, optional, defaults to False) — Whether or not to return a ModelOutput instead of a plain tuple.
synced_gpus (bool, optional, defaults to False) — Whether to continue running the while loop until max_length (needed for ZeRO stage 3) model_kwargs — Additional model specific kwargs will be forwarded to the forward function of the model. If model is an encoder-decoder model the kwargs should include encoder_outputs.

Generates sequences of token ids for models with a language modeling head using beam search multinomial sampling and can be used for text-decoder, text-to-text, speech-to-text, and vision-to-text models.

In most cases, you do not need to call beam_sample() directly. Use generate() instead. For an overview of generation strategies and code examples, check the following guide.

Examples:

>>> from transformers import (
...     AutoTokenizer,
...     AutoModelForSeq2SeqLM,
...     LogitsProcessorList,
...     MinLengthLogitsProcessor,
...     TopKLogitsWarper,
...     TemperatureLogitsWarper,
...     BeamSearchScorer,
... )
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-base")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("google-t5/t5-base")

>>> encoder_input_str = "translate English to German: How old are you?"
>>> encoder_input_ids = tokenizer(encoder_input_str, return_tensors="pt").input_ids

>>> # lets run beam search using 3 beams
>>> num_beams = 3
>>> # define decoder start token ids
>>> input_ids = torch.ones((num_beams, 1), device=model.device, dtype=torch.long)
>>> input_ids = input_ids * model.config.decoder_start_token_id

>>> # add encoder_outputs to model keyword arguments
>>> model_kwargs = {
...     "encoder_outputs": model.get_encoder()(
...         encoder_input_ids.repeat_interleave(num_beams, dim=0), return_dict=True
...     )
... }

>>> # instantiate beam scorer
>>> beam_scorer = BeamSearchScorer(
...     batch_size=1,
...     max_length=model.config.max_length,
...     num_beams=num_beams,
...     device=model.device,
... )

>>> # instantiate logits processors
>>> logits_processor = LogitsProcessorList(
...     [MinLengthLogitsProcessor(5, eos_token_id=model.config.eos_token_id)]
... )
>>> # instantiate logits processors
>>> logits_warper = LogitsProcessorList(
...     [
...         TopKLogitsWarper(50),
...         TemperatureLogitsWarper(0.7),
...     ]
... )

>>> outputs = model.beam_sample(
...     input_ids, beam_scorer, logits_processor=logits_processor, logits_warper=logits_warper, **model_kwargs
... )

>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Wie alt bist du?']

contrastive_search

( input_ids: LongTensor top_k: Optional = 1 penalty_alpha: Optional = 0 logits_processor: Optional = None logits_warper: Optional = None stopping_criteria: Optional = None pad_token_id: Optional = None eos_token_id: Union = None output_attentions: Optional = None output_hidden_states: Optional = None output_scores: Optional = None output_logits: Optional = None return_dict_in_generate: Optional = None synced_gpus: bool = False streamer: Optional = None sequential: Optional = None **model_kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — The sequence used as a prompt for the generation.
top_k (int, optional, defaults to 1) — The size of the candidate set that is used to re-rank for contrastive search
penalty_alpha (float, optional, defaults to 0) — The degeneration penalty for contrastive search; activate when it is larger than 0
logits_processor (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsProcessor used to modify the prediction scores of the language modeling head applied at each generation step.
logits_warper (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsWarper used to warp the prediction score distribution of the language modeling head applied before multinomial sampling at each generation step.
stopping_criteria (StoppingCriteriaList, optional) — An instance of StoppingCriteriaList. List of instances of class derived from StoppingCriteria used to tell if the generation loop should stop.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (Union[int, List[int]], optional) — The id of the end-of-sequence token. Optionally, use a list to set multiple end-of-sequence tokens.
output_attentions (bool, optional, defaults to False) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more details.
output_hidden_states (bool, optional, defaults to False) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more details.
output_scores (bool, optional, defaults to False) — Whether or not to return the prediction scores. See scores under returned tensors for more details.
output_logits (bool, optional, defaults to False) — Whether or not to return the raw prediction logit scores. See logits under returned tensors for more details.
return_dict_in_generate (bool, optional, defaults to False) — Whether or not to return a ModelOutput instead of a plain tuple.
synced_gpus (bool, optional, defaults to False) — Whether to continue running the while loop until max_length (needed for ZeRO stage 3)
streamer (BaseStreamer, optional) — Streamer object that will be used to stream the generated sequences. Generated tokens are passed through streamer.put(token_ids) and the streamer is responsible for any further processing.
sequential (bool, optional) — Switches topk hidden state computation from parallel to sequential to reduce memory if True. model_kwargs — Additional model specific keyword arguments will be forwarded to the forward function of the model. If model is an encoder-decoder model the kwargs should include encoder_outputs.

Generates sequences of token ids for models with a language modeling head using contrastive search and can be used for text-decoder, text-to-text, speech-to-text, and vision-to-text models.

In most cases, you do not need to call contrastive_search() directly. Use generate() instead. For an overview of generation strategies and code examples, check the following guide.

Examples:

>>> from transformers import (
...     AutoTokenizer,
...     AutoModelForCausalLM,
...     StoppingCriteriaList,
...     MaxLengthCriteria,
... )

>>> tokenizer = AutoTokenizer.from_pretrained("facebook/opt-125m")
>>> model = AutoModelForCausalLM.from_pretrained("facebook/opt-125m")
>>> # set pad_token_id to eos_token_id because OPT does not have a PAD token
>>> model.config.pad_token_id = model.config.eos_token_id
>>> input_prompt = "DeepMind Company is"
>>> input_ids = tokenizer(input_prompt, return_tensors="pt")
>>> stopping_criteria = StoppingCriteriaList([MaxLengthCriteria(max_length=64)])
>>> outputs = model.contrastive_search(
...     **input_ids, penalty_alpha=0.6, top_k=4, stopping_criteria=stopping_criteria
... )
>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['DeepMind Company is a company that focuses on the development and commercialization of artificial intelligence (AI). DeepMind’s mission is to help people understand and solve problems that are difficult to solve in the world today.\n\nIn this post, we talk about the benefits of deep learning in business and how it']

group_beam_search

( input_ids: LongTensor beam_scorer: BeamScorer logits_processor: Optional = None stopping_criteria: Optional = None max_length: Optional = None pad_token_id: Optional = None eos_token_id: Union = None output_attentions: Optional = None output_hidden_states: Optional = None output_scores: Optional = None output_logits: Optional = None return_dict_in_generate: Optional = None synced_gpus: bool = False **model_kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — The sequence used as a prompt for the generation.
beam_scorer (BeamScorer) — An derived instance of BeamScorer that defines how beam hypotheses are constructed, stored and sorted during generation. For more information, the documentation of BeamScorer should be read.
logits_processor (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsProcessor used to modify the prediction scores of the language modeling head applied at each generation step.
stopping_criteria (StoppingCriteriaList, optional) — An instance of StoppingCriteriaList. List of instances of class derived from StoppingCriteria used to tell if the generation loop should stop.
max_length (int, optional, defaults to 20) — DEPRECATED. Use logits_processor or stopping_criteria directly to cap the number of generated tokens. The maximum length of the sequence to be generated.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (Union[int, List[int]], optional) — The id of the end-of-sequence token. Optionally, use a list to set multiple end-of-sequence tokens.
output_attentions (bool, optional, defaults to False) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more details.
output_hidden_states (bool, optional, defaults to False) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more details.
output_scores (bool, optional, defaults to False) — Whether or not to return the prediction scores. See scores under returned tensors for more details.
output_logits (bool, optional, defaults to False) — Whether or not to return the raw prediction logit scores. See logits under returned tensors for more details.
return_dict_in_generate (bool, optional, defaults to False) — Whether or not to return a ModelOutput instead of a plain tuple.
synced_gpus (bool, optional, defaults to False) — Whether to continue running the while loop until max_length (needed for ZeRO stage 3)

model_kwargs — Additional model specific kwargs that will be forwarded to the forward function of the model. If model is an encoder-decoder model the kwargs should include encoder_outputs.

Generates sequences of token ids for models with a language modeling head using diverse beam search decoding and can be used for text-decoder, text-to-text, speech-to-text, and vision-to-text models.

In most cases, you do not need to call group_beam_search() directly. Use generate() instead. For an overview of generation strategies and code examples, check the following guide.

Examples:

>>> from transformers import (
...     AutoTokenizer,
...     AutoModelForSeq2SeqLM,
...     LogitsProcessorList,
...     MinLengthLogitsProcessor,
...     HammingDiversityLogitsProcessor,
...     BeamSearchScorer,
... )
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-base")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("google-t5/t5-base")

>>> encoder_input_str = "translate English to German: How old are you?"
>>> encoder_input_ids = tokenizer(encoder_input_str, return_tensors="pt").input_ids


>>> # lets run diverse beam search using 6 beams
>>> num_beams = 6
>>> # define decoder start token ids
>>> input_ids = torch.ones((num_beams, 1), device=model.device, dtype=torch.long)
>>> input_ids = input_ids * model.config.decoder_start_token_id

>>> # add encoder_outputs to model keyword arguments
>>> model_kwargs = {
...     "encoder_outputs": model.get_encoder()(
...         encoder_input_ids.repeat_interleave(num_beams, dim=0), return_dict=True
...     )
... }

>>> # instantiate beam scorer
>>> beam_scorer = BeamSearchScorer(
...     batch_size=1,
...     max_length=model.config.max_length,
...     num_beams=num_beams,
...     device=model.device,
...     num_beam_groups=3,
... )

>>> # instantiate logits processors
>>> logits_processor = LogitsProcessorList(
...     [
...         HammingDiversityLogitsProcessor(5.5, num_beams=6, num_beam_groups=3),
...         MinLengthLogitsProcessor(5, eos_token_id=model.config.eos_token_id),
...     ]
... )

>>> outputs = model.group_beam_search(
...     input_ids, beam_scorer, logits_processor=logits_processor, **model_kwargs
... )

>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Wie alt bist du?']

constrained_beam_search

( input_ids: LongTensor constrained_beam_scorer: ConstrainedBeamSearchScorer logits_processor: Optional = None stopping_criteria: Optional = None max_length: Optional = None pad_token_id: Optional = None eos_token_id: Union = None output_attentions: Optional = None output_hidden_states: Optional = None output_scores: Optional = None output_logits: Optional = None return_dict_in_generate: Optional = None synced_gpus: Optional = None **model_kwargs )

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — The sequence used as a prompt for the generation.
constrained_beam_scorer (ConstrainedBeamSearchScorer) — A derived instance of BeamScorer that defines how beam hypotheses are constructed, stored and sorted during generation, while satisfying a list of positive constraints. For more information, the documentation of ConstrainedBeamSearchScorer should be read.
logits_processor (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsProcessor used to modify the prediction scores of the language modeling head applied at each generation step.
stopping_criteria (StoppingCriteriaList, optional) — An instance of StoppingCriteriaList. List of instances of class derived from StoppingCriteria used to tell if the generation loop should stop.
logits_warper (LogitsProcessorList, optional) — An instance of LogitsProcessorList. List of instances of class derived from LogitsWarper used to warp the prediction score distribution of the language modeling head applied before multinomial sampling at each generation step.
max_length (int, optional, defaults to 20) — DEPRECATED. Use logits_processor or stopping_criteria directly to cap the number of generated tokens. The maximum length of the sequence to be generated.
pad_token_id (int, optional) — The id of the padding token.
eos_token_id (Union[int, List[int]], optional) — The id of the end-of-sequence token. Optionally, use a list to set multiple end-of-sequence tokens.
output_attentions (bool, optional, defaults to False) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more details.
output_hidden_states (bool, optional, defaults to False) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more details.
output_scores (bool, optional, defaults to False) — Whether or not to return the prediction scores. See scores under returned tensors for more details.
output_logits (bool, optional, defaults to False) — Whether or not to return the raw prediction logit scores. See logits under returned tensors for more details.
return_dict_in_generate (bool, optional, defaults to False) — Whether or not to return a ModelOutput instead of a plain tuple.
synced_gpus (bool, optional, defaults to False) — Whether to continue running the while loop until max_length (needed for ZeRO stage 3) model_kwargs — Additional model specific kwargs will be forwarded to the forward function of the model. If model is an encoder-decoder model the kwargs should include encoder_outputs.

Generates sequences of token ids for models with a language modeling head using constrained beam search decoding and can be used for text-decoder, text-to-text, speech-to-text, and vision-to-text models.

In most cases, you do not need to call constrained_beam_search() directly. Use generate() instead. For an overview of generation strategies and code examples, check the following guide.

Examples:

>>> from transformers import (
...     AutoTokenizer,
...     AutoModelForSeq2SeqLM,
...     LogitsProcessorList,
...     MinLengthLogitsProcessor,
...     ConstrainedBeamSearchScorer,
...     PhrasalConstraint,
... )
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-base")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("google-t5/t5-base")

>>> encoder_input_str = "translate English to German: How old are you?"
>>> encoder_input_ids = tokenizer(encoder_input_str, return_tensors="pt").input_ids


>>> # lets run beam search using 3 beams
>>> num_beams = 3
>>> # define decoder start token ids
>>> input_ids = torch.ones((num_beams, 1), device=model.device, dtype=torch.long)
>>> input_ids = input_ids * model.config.decoder_start_token_id

>>> # add encoder_outputs to model keyword arguments
>>> model_kwargs = {
...     "encoder_outputs": model.get_encoder()(
...         encoder_input_ids.repeat_interleave(num_beams, dim=0), return_dict=True
...     )
... }

>>> constraint_str = "Sie"
>>> constraint_token_ids = tokenizer.encode(constraint_str)[:-1]  # slice to remove eos token
>>> constraints = [PhrasalConstraint(token_ids=constraint_token_ids)]


>>> # instantiate beam scorer
>>> beam_scorer = ConstrainedBeamSearchScorer(
...     batch_size=1, num_beams=num_beams, device=model.device, constraints=constraints
... )

>>> # instantiate logits processors
>>> logits_processor = LogitsProcessorList(
...     [
...         MinLengthLogitsProcessor(5, eos_token_id=model.config.eos_token_id),
...     ]
... )

>>> outputs = model.constrained_beam_search(
...     input_ids, beam_scorer, constraints=constraints, logits_processor=logits_processor, **model_kwargs
... )

>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Wie alt sind Sie?']

TFGenerationMixin

class transformers.TFGenerationMixin

( )

A class containing all of the functions supporting generation, to be used as a mixin in TFPreTrainedModel.

The class exposes generate(), which can be used for:

greedy decoding by calling greedy_search() if num_beams=1 and do_sample=False
contrastive search by calling contrastive_search() if penalty_alpha>0 and top_k>1
multinomial sampling by calling sample() if num_beams=1 and do_sample=True
beam-search decoding by calling beam_search() if num_beams>1

You do not need to call any of the above methods directly. Pass custom parameter values to ‘generate’ instead. To learn more about decoding strategies refer to the text generation strategies guide.

generate

( inputs: Optional = None generation_config: Optional = None logits_processor: Optional = None seed = None **kwargs ) → ModelOutput or tf.Tensor

Parameters

inputs (tf.Tensor of varying shape depending on the modality, optional) — The sequence used as a prompt for the generation or as model inputs to the encoder. If None the method initializes it with bos_token_id and a batch size of 1. For decoder-only models inputs should of in the format of input_ids. For encoder-decoder models inputs can represent any of input_ids, input_values, input_features, or pixel_values.
generation_config (~generation.GenerationConfig, optional) — The generation configuration to be used as base parametrization for the generation call. **kwargs passed to generate matching the attributes of generation_config will override them. If generation_config is not provided, the default will be used, which had the following loading priority: 1) from the generation_config.json model file, if it exists; 2) from the model configuration. Please note that unspecified parameters will inherit GenerationConfig’s default values, whose documentation should be checked to parameterize generation.
logits_processor (LogitsProcessorList, optional) — Custom logits processors that complement the default logits processors built from arguments and generation config. If a logit processor is passed that is already created with the arguments or a generation config an error is thrown. This feature is intended for advanced users.
seed (List[int], optional) — Random seed to control sampling, containing two integers, used when do_sample is True. See the seed argument from stateless functions in tf.random.
kwargs (Dict[str, Any], optional) — Ad hoc parametrization of generate_config and/or additional model-specific kwargs that will be forwarded to the forward function of the model. If the model is an encoder-decoder model, encoder specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with decoder_.

Returns

ModelOutput or tf.Tensor

A ModelOutput (if return_dict_in_generate=True or when config.return_dict_in_generate=True) or a tf.Tensor.

If the model is not an encoder-decoder model (model.config.is_encoder_decoder=False), the possible ModelOutput types are:

If the model is an encoder-decoder model (model.config.is_encoder_decoder=True), the possible ModelOutput types are:

Generates sequences of token ids for models with a language modeling head.

Most generation-controlling parameters are set in generation_config which, if not passed, will be set to the model’s default generation configuration. You can override any generation_config by passing the corresponding parameters to generate, e.g. .generate(inputs, num_beams=4, do_sample=True).

For an overview of generation strategies and code examples, check out the following guide.

compute_transition_scores

( sequences: Tensor scores: Tuple beam_indices: Optional = None normalize_logits: bool = False ) → tf.Tensor

Parameters

sequences (tf.Tensor) — The generated sequences. The second dimension (sequence_length) is either equal to max_length or shorter if all batches finished early due to the eos_token_id.
scores (tuple(tf.Tensor)) — 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 Tuple of tf.Tensor with up to max_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) — Beam indices of generated token id at each generation step. tf.Tensor of shape (batch_size*num_return_sequences, sequence_length). Only required if a num_beams>1 at generate-time.
normalize_logits (bool, optional, defaults to False) — Whether to normalize the logits (which, for legacy reasons, may be unnormalized).

Returns

tf.Tensor

A tf.Tensor of shape (batch_size*num_return_sequences, sequence_length) containing the transition scores (logits)

Computes the transition scores of sequences given the generation scores (and beam indices, if beam search was used). This is a convenient method to quicky obtain the scores of the selected tokens at generation time.

Examples:

>>> from transformers import GPT2Tokenizer, TFAutoModelForCausalLM
>>> import numpy as np

>>> tokenizer = GPT2Tokenizer.from_pretrained("openai-community/gpt2")
>>> model = TFAutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> tokenizer.pad_token_id = tokenizer.eos_token_id
>>> inputs = tokenizer(["Today is"], return_tensors="tf")

>>> # Example 1: Print the scores for each token generated with Greedy Search
>>> outputs = model.generate(**inputs, max_new_tokens=5, return_dict_in_generate=True, output_scores=True)
>>> transition_scores = model.compute_transition_scores(
...     outputs.sequences, outputs.scores, normalize_logits=True
... )
>>> # input_length is the length of the input prompt for decoder-only models, like the GPT family, and 1 for
>>> # encoder-decoder models, like BART or T5.
>>> input_length = 1 if model.config.is_encoder_decoder else inputs.input_ids.shape[1]
>>> generated_tokens = outputs.sequences[:, input_length:]
>>> for tok, score in zip(generated_tokens[0], transition_scores[0]):
...     # | token | token string | logits | probability
...     print(f"| {tok:5d} | {tokenizer.decode(tok):8s} | {score.numpy():.3f} | {np.exp(score.numpy()):.2%}")
|   262 |  the     | -1.413 | 24.33%
|  1110 |  day     | -2.609 | 7.36%
|   618 |  when    | -2.009 | 13.41%
|   356 |  we      | -1.859 | 15.58%
|   460 |  can     | -2.508 | 8.14%

>>> # Example 2: Reconstruct the sequence scores from Beam Search
>>> outputs = model.generate(
...     **inputs,
...     max_new_tokens=5,
...     num_beams=4,
...     num_return_sequences=4,
...     return_dict_in_generate=True,
...     output_scores=True,
... )
>>> transition_scores = model.compute_transition_scores(
...     outputs.sequences, outputs.scores, outputs.beam_indices, normalize_logits=False
... )
>>> # If you sum the generated tokens' scores and apply the length penalty, you'll get the sequence scores.
>>> # Tip: recomputing the scores is only guaranteed to match with `normalize_logits=False`. Depending on the
>>> # use case, you might want to recompute it with `normalize_logits=True`.
>>> output_length = input_length + np.sum(transition_scores.numpy() < 0, axis=1)
>>> length_penalty = model.generation_config.length_penalty
>>> reconstructed_scores = np.sum(transition_scores, axis=1) / (output_length**length_penalty)
>>> print(np.allclose(outputs.sequences_scores, reconstructed_scores))
True

FlaxGenerationMixin

class transformers.FlaxGenerationMixin

( )

A class containing all functions for auto-regressive text generation, to be used as a mixin in FlaxPreTrainedModel.

The class exposes generate(), which can be used for:

greedy decoding by calling _greedy_search() if num_beams=1 and do_sample=False
multinomial sampling by calling _sample() if num_beams=1 and do_sample=True
beam-search decoding by calling _beam_search() if num_beams>1 and do_sample=False

You do not need to call any of the above methods directly. Pass custom parameter values to ‘generate’ instead. To learn more about decoding strategies refer to the text generation strategies guide.

generate

( input_ids: Array generation_config: Optional = None prng_key: Optional = None trace: bool = True params: Optional = None logits_processor: Optional = None **kwargs )

Parameters

input_ids (jnp.ndarray of shape (batch_size, sequence_length)) — The sequence used as a prompt for the generation.
generation_config (~generation.GenerationConfig, optional) — The generation configuration to be used as base parametrization for the generation call. **kwargs passed to generate matching the attributes of generation_config will override them. If generation_config is not provided, the default will be used, which had the following loading priority: 1) from the generation_config.json model file, if it exists; 2) from the model configuration. Please note that unspecified parameters will inherit GenerationConfig’s default values, whose documentation should be checked to parameterize generation.
trace (bool, optional, defaults to True) — Whether to trace generation. Setting trace=False should only be used for debugging and will lead to a considerably slower runtime.
params (Dict[str, jnp.ndarray], optional) — Optionally the model parameters can be passed. Can be useful for parallelized generation.
logits_processor (FlaxLogitsProcessorList , optional) — Custom logits processors that complement the default logits processors built from arguments and generation config. If a logit processor is passed that is already created with the arguments or a generation config an error is thrown. This feature is intended for advanced users.
kwargs (Dict[str, Any], optional) — Ad hoc parametrization of generate_config and/or additional model-specific kwargs that will be forwarded to the forward function of the model. If the model is an encoder-decoder model, encoder specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with decoder_.

Generates sequences of token ids for models with a language modeling head.

←Models ONNX→