Transformers 4.37 中文文档（九十九）（5）

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

>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> set_seed(0)
>>> model = AutoModelForCausalLM.from_pretrained("distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("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, 0, 2, 2. 2, 2, 2, 2
>>> # 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

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( exponential_decay_length_penalty: Tuple eos_token_id: Union input_ids_seq_length: int )

>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> model = AutoModelForCausalLM.from_pretrained("gpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("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|>

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( bos_token_id: int )

>>> 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>

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( max_length: int eos_token_id: Union )

>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained("distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("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|>

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( force_token_map: List )

>>> 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")
>>> # This Whisper model forces the generation to start with `50362` at the first position by default, i.e.
>>> # `"forced_decoder_ids": [[1, 50362]]`. This means all other tokens are masked out.
>>> outputs = model.generate(**inputs, return_dict_in_generate=True, output_scores=True)
>>> print(
...     all(outputs.scores[0][0, i] == float("-inf") for i in range(processor.tokenizer.vocab_size) if i != 50362)
... )
True
>>> print(outputs.scores[0][0, 50362])
tensor(0.)
>>> # If we disable `forced_decoder_ids`, we stop seeing that effect
>>> outputs = model.generate(**inputs, return_dict_in_generate=True, output_scores=True, forced_decoder_ids=None)
>>> print(
...     all(outputs.scores[0][0, i] == float("-inf") for i in range(processor.tokenizer.vocab_size) if i != 50362)
... )
False
>>> print(outputs.scores[0][0, 50362])
tensor(19.3140)

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( diversity_penalty: float num_beams: int num_beam_groups: int )

>>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
>>> import torch
>>> # Initialize the model and tokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("t5-base")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("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.']

( input_ids: LongTensor scores: FloatTensor current_tokens: LongTensor beam_group_idx: int ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( )

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( )

>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> import torch
>>> model = AutoModelForCausalLM.from_pretrained("distilgpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("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.sum(torch.exp(outputs.scores[-1])))
tensor(816.3250)
>>> # 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.sum(torch.exp(outputs.scores[-1])))
tensor(1.0000)

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( )

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( iterable = () )

( input_ids: LongTensor scores: FloatTensor **kwargs ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size

( )

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( min_length: int eos_token_id: Union )

>>> 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

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)

( prompt_length_to_skip: int min_new_tokens: int eos_token_id: Union )

>>> 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

( input_ids: LongTensor scores: FloatTensor ) → export const metadata = 'undefined';torch.FloatTensor of shape (batch_size, config.vocab_size)