>>> 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)

>>> 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.

>>> 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.

>>> 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 recommends 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

>>> 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 recommends 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

>>> 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|>

>>> 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>

>>> 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|>

>>> 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

>>> 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

>>> 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

>>> 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

>>> 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.

>>> 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

>>> 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 constrain 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

>>> from transformers import AutoTokenizer, AutoModelForCausalLM, RepetitionPenaltyLogitsProcessor

>>> # 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

>>> # We can also exclude the input prompt by creating an instance of this class
>>> # with a `prompt_ignore_length` and passing it as a custom logit processor
>>> rep_pen_processor = RepetitionPenaltyLogitsProcessor(
...     penalty=1.1,
...     prompt_ignore_length=inputs["input_ids"].shape[-1]
... )
>>> penalized_ids = model.generate(**inputs, logits_processor=[rep_pen_processor])
>>> print(tokenizer.batch_decode(penalized_ids, skip_special_tokens=True)[0])
I'm not going to be able to do that. I'm going to have to go through a lot of things, and

>>> from transformers import AutoTokenizer, AutoModelForCausalLM

>>> model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
>>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
>>> inputs = tokenizer(["The full name of Donald is Donald"], return_tensors="pt")

>>> summary_ids = model.generate(inputs["input_ids"], max_new_tokens=4, do_sample=False)
>>> print(tokenizer.batch_decode(summary_ids, skip_special_tokens=True)[0])
The full name of Donald is Donald John Trump Sr.

>>> def get_tokens(word):
...     return tokenizer([word], add_special_tokens=False).input_ids[0]

>>> # IMPORTANT: Remember our tip about adding spaces before words to bias them correctly.
>>> sequence_bias = [[get_tokens("Trump"), -10.0],]  # will fail to apply bias
>>> biased_ids = model.generate(
...     inputs["input_ids"], max_new_tokens=4, do_sample=False, sequence_bias=sequence_bias
... )
>>> print(tokenizer.batch_decode(biased_ids, skip_special_tokens=True)[0])
The full name of Donald is Donald John Trump Sr.

>>> sequence_bias = [[get_tokens(" Trump"), -10.0],]  # will work
>>> biased_ids = model.generate(
...     inputs["input_ids"], max_new_tokens=4, do_sample=False, sequence_bias=sequence_bias
... )
>>> print(tokenizer.batch_decode(biased_ids, skip_special_tokens=True)[0])
The full name of Donald is Donald John Harper. He

>>> # We can also add a positive bias to nudge the model towards specific tokens or continuations. This technique
>>> # is also more effective when paired up with beam search.
>>> sequence_bias = [[get_tokens(" Donald Duck"), 10.0],]
>>> biased_ids = model.generate(
...     inputs["input_ids"], max_new_tokens=4, num_beams=4, do_sample=False, sequence_bias=sequence_bias
... )
>>> print(tokenizer.batch_decode(biased_ids, skip_special_tokens=True)[0])
The full name of Donald is Donald Duck. He is

>>> 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)

>>> 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)

>>> 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)

>>> 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']

>>> from transformers import AutoTokenizer, AutoModelForCausalLM

>>> model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B")

>>> inputs = tokenizer("A sequence: 1, 2", return_tensors="pt")

>>> outputs = model.generate(**inputs, do_sample=True, top_h=0.4)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])
A sequence: 1, 2, 3, 4, 5, 6, 7, 8, 9

>>> 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

>>> 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

>>> 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)

>>> 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"

>>> 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 sequence on, in this case it's the word "can"(460)
>>> model.generation_config.eos_token_id = 460
>>> generated_ids = model.generate(inputs=input_features,return_timestamps=False)
>>> transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
>>> print("Transcription:", transcription)
Transcription:  He has grave doubts whether Sir Frederick Layton's work is really Greek after all and can

>>> from transformers import AutoTokenizer, AutoModelForCausalLM, WatermarkingConfig

>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> inputs = tokenizer(["Alice and Bob are"], return_tensors="pt")

>>> # normal generation
>>> out = model.generate(inputs["input_ids"], max_length=20, do_sample=False)
>>> tokenizer.batch_decode(out, skip_special_tokens=True)[0]
'Alice and Bob are both in the same room.\n\n"I\'m not sure if you\'re'

>>> # watermarked generation
>>> watermarking_config = WatermarkingConfig(bias=2.5, context_width=2, seeding_scheme="selfhash")
>>> out = model.generate(inputs["input_ids"], watermarking_config=watermarking_config, max_length=20, do_sample=False)
>>> tokenizer.batch_decode(out, skip_special_tokens=True)[0]
'Alice and Bob are both still alive and well and the story is pretty much a one-hour adventure'

>>> # to detect watermarked text use the WatermarkDetector class
>>> from transformers import WatermarkDetector
>>> detector = WatermarkDetector(model_config=model.config, device="cpu", watermarking_config= watermarking_config)
>>> detection_preds = detector(out)
>>> detection_preds
array([ True])

>>> from transformers import AutoModelForCausalLM, AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2")
>>> model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2")
>>> inputs = tokenizer("The biggest states in the USA by land area:", return_tensors="pt")

>>> gen_out = model.generate(**inputs)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
The biggest states in the USA by land area:
- Alaska
- Texas
- California

>>> # Passing one or more stop strings will halt generation after those strings are emitted
>>> # Note that generating with stop strings requires you to pass the tokenizer too
>>> gen_out = model.generate(**inputs, stop_strings=["Texas"], tokenizer=tokenizer)
>>> print(tokenizer.batch_decode(gen_out, skip_special_tokens=True)[0])
The biggest states in the USA by land area:
- Alaska
- Texas

>>> from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

>>> tok = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> inputs = tok(["An increasing sequence: one,"], return_tensors="pt")
>>> streamer = TextStreamer(tok)

>>> # Despite returning the usual output, the streamer will also print the generated text to stdout.
>>> _ = model.generate(**inputs, streamer=streamer, max_new_tokens=20)
An increasing sequence: one, two, three, four, five, six, seven, eight, nine, ten, eleven,

>>> from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
>>> from threading import Thread

>>> tok = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> inputs = tok(["An increasing sequence: one,"], return_tensors="pt")
>>> streamer = TextIteratorStreamer(tok)

>>> # Run the generation in a separate thread, so that we can fetch the generated text in a non-blocking way.
>>> generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=20)
>>> thread = Thread(target=model.generate, kwargs=generation_kwargs)
>>> thread.start()
>>> generated_text = ""
>>> for new_text in streamer:
...     generated_text += new_text
>>> generated_text
'An increasing sequence: one, two, three, four, five, six, seven, eight, nine, ten, eleven,'

>>> from transformers import AutoModelForCausalLM, AutoTokenizer, AsyncTextIteratorStreamer
>>> from threading import Thread
>>> import asyncio

>>> tok = AutoTokenizer.from_pretrained("openai-community/gpt2")
>>> model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
>>> inputs = tok(["An increasing sequence: one,"], return_tensors="pt")

>>> # Run the generation in a separate thread, so that we can fetch the generated text in a non-blocking way.
>>> async def main():
...     # Important: AsyncTextIteratorStreamer must be initialized inside a coroutine!
...     streamer = AsyncTextIteratorStreamer(tok)
...     generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=20)
...     thread = Thread(target=model.generate, kwargs=generation_kwargs)
...     thread.start()
...     generated_text = ""
...     async for new_text in streamer:
...         generated_text += new_text
>>>     print(generated_text)
>>> asyncio.run(main())
An increasing sequence: one, two, three, four, five, six, seven, eight, nine, ten, eleven,