>>> from transformers import AutoModelForCausalLM

>>> model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
>>> model.generation_config
GenerationConfig {
    "bos_token_id": 50256,
    "eos_token_id": 50256,
}

>>> my_model.generate(**inputs, num_beams=4, do_sample=True)

>>> from transformers import AutoModelForCausalLM, GenerationConfig

>>> model = AutoModelForCausalLM.from_pretrained("my_account/my_model")
>>> generation_config = GenerationConfig(
...     max_new_tokens=50, do_sample=True, top_k=50, eos_token_id=model.config.eos_token_id
... )
>>> generation_config.save_pretrained("my_account/my_model", push_to_hub=True)

>>> from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, GenerationConfig

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

>>> translation_generation_config = GenerationConfig(
...     num_beams=4,
...     early_stopping=True,
...     decoder_start_token_id=0,
...     eos_token_id=model.config.eos_token_id,
...     pad_token=model.config.pad_token_id,
... )

>>> # Tip: add `push_to_hub=True` to push to the Hub
>>> translation_generation_config.save_pretrained("/tmp", "translation_generation_config.json")

>>> # You could then use the named generation config file to parameterize generation
>>> generation_config = GenerationConfig.from_pretrained("/tmp", "translation_generation_config.json")
>>> inputs = tokenizer("translate English to French: Configuration files are easy to use!", return_tensors="pt")
>>> outputs = model.generate(**inputs, generation_config=generation_config)
>>> print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
['Les fichiers de configuration sont faciles à utiliser!']

>>> 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

>>> prompt = "I look forward to"
>>> checkpoint = "distilbert/distilgpt2"

>>> tokenizer = AutoTokenizer.from_pretrained(checkpoint)
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> model = AutoModelForCausalLM.from_pretrained(checkpoint)
>>> outputs = model.generate(**inputs)
>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['I look forward to seeing you all again!\n\n\n\n\n\n\n\n\n\n\n']

>>> from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed
>>> set_seed(0)  # For reproducibility

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

>>> prompt = "Today was an amazing day because"
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> outputs = model.generate(**inputs, do_sample=True, num_beams=1, max_new_tokens=100)
>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Today was an amazing day because when you go to the World Cup and you don\'t, or when you don\'t get invited,
that\'s a terrible feeling."']

>>> from transformers import AutoModelForCausalLM, AutoTokenizer

>>> prompt = "It is astonishing how one can"
>>> checkpoint = "openai-community/gpt2-medium"

>>> tokenizer = AutoTokenizer.from_pretrained(checkpoint)
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> model = AutoModelForCausalLM.from_pretrained(checkpoint)

>>> outputs = model.generate(**inputs, num_beams=5, max_new_tokens=50)
>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['It is astonishing how one can have such a profound impact on the lives of so many people in such a short period of
time."\n\nHe added: "I am very proud of the work I have been able to do in the last few years.\n\n"I have']

>>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, set_seed
>>> set_seed(0)  # For reproducibility

>>> prompt = "translate English to German: The house is wonderful."
>>> checkpoint = "google-t5/t5-small"

>>> tokenizer = AutoTokenizer.from_pretrained(checkpoint)
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)

>>> outputs = model.generate(**inputs, num_beams=5, do_sample=True)
>>> tokenizer.decode(outputs[0], skip_special_tokens=True)
'Das Haus ist wunderbar.'

>>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

>>> checkpoint = "google/pegasus-xsum"
>>> prompt = (
...     "The Permaculture Design Principles are a set of universal design principles "
...     "that can be applied to any location, climate and culture, and they allow us to design "
...     "the most efficient and sustainable human habitation and food production systems. "
...     "Permaculture is a design system that encompasses a wide variety of disciplines, such "
...     "as ecology, landscape design, environmental science and energy conservation, and the "
...     "Permaculture design principles are drawn from these various disciplines. Each individual "
...     "design principle itself embodies a complete conceptual framework based on sound "
...     "scientific principles. When we bring all these separate  principles together, we can "
...     "create a design system that both looks at whole systems, the parts that these systems "
...     "consist of, and how those parts interact with each other to create a complex, dynamic, "
...     "living system. Each design principle serves as a tool that allows us to integrate all "
...     "the separate parts of a design, referred to as elements, into a functional, synergistic, "
...     "whole system, where the elements harmoniously interact and work together in the most "
...     "efficient way possible."
... )

>>> tokenizer = AutoTokenizer.from_pretrained(checkpoint)
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)

>>> outputs = model.generate(**inputs, num_beams=5, num_beam_groups=5, max_new_tokens=30, diversity_penalty=1.0)
>>> tokenizer.decode(outputs[0], skip_special_tokens=True)
'The Design Principles are a set of universal design principles that can be applied to any location, climate and
culture, and they allow us to design the'

>>> from transformers import AutoModelForCausalLM, AutoTokenizer

>>> prompt = "Alice and Bob"
>>> checkpoint = "EleutherAI/pythia-1.4b-deduped"
>>> assistant_checkpoint = "EleutherAI/pythia-160m-deduped"

>>> tokenizer = AutoTokenizer.from_pretrained(checkpoint)
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> model = AutoModelForCausalLM.from_pretrained(checkpoint)
>>> assistant_model = AutoModelForCausalLM.from_pretrained(assistant_checkpoint)
>>> outputs = model.generate(**inputs, assistant_model=assistant_model)
>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Alice and Bob are sitting in a bar. Alice is drinking a beer and Bob is drinking a']

>>> from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
>>> set_seed(42)  # For reproducibility

>>> prompt = "Alice and Bob"
>>> checkpoint = "EleutherAI/pythia-1.4b-deduped"
>>> assistant_checkpoint = "EleutherAI/pythia-160m-deduped"

>>> tokenizer = AutoTokenizer.from_pretrained(checkpoint)
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> model = AutoModelForCausalLM.from_pretrained(checkpoint)
>>> assistant_model = AutoModelForCausalLM.from_pretrained(assistant_checkpoint)
>>> outputs = model.generate(**inputs, assistant_model=assistant_model, do_sample=True, temperature=0.5)
>>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
['Alice and Bob are going to the same party. It is a small party, in a small']