Transformers 4.37 中文文档（二）（3）

agent.chat("Generate a picture of rivers and lakes")

agent.chat("Transform the picture so that there is a rock in there")

from transformers import load_tool
tool = load_tool("text-to-speech")
audio = tool("This is a text to speech tool")

agent.run("Draw me a picture of rivers and lakes", return_code=True)

from transformers import load_tool
image_generator = load_tool("huggingface-tools/text-to-image")
image = image_generator(prompt="rivers and lakes")

pip install transformers bitsandbytes>=0.39.0 -q

>>> from transformers import AutoModelForCausalLM
>>> model = AutoModelForCausalLM.from_pretrained(
...     "mistralai/Mistral-7B-v0.1", device_map="auto", load_in_4bit=True
... )

>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1", padding_side="left")
>>> model_inputs = tokenizer(["A list of colors: red, blue"], return_tensors="pt").to("cuda")

>>> generated_ids = model.generate(**model_inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
'A list of colors: red, blue, green, yellow, orange, purple, pink,'

>>> tokenizer.pad_token = tokenizer.eos_token  # Most LLMs don't have a pad token by default
>>> model_inputs = tokenizer(
...     ["A list of colors: red, blue", "Portugal is"], return_tensors="pt", padding=True
... ).to("cuda")
>>> generated_ids = model.generate(**model_inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
['A list of colors: red, blue, green, yellow, orange, purple, pink,',
'Portugal is a country in southwestern Europe, on the Iber']

>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
>>> tokenizer.pad_token = tokenizer.eos_token  # Most LLMs don't have a pad token by default
>>> model = AutoModelForCausalLM.from_pretrained(
...     "mistralai/Mistral-7B-v0.1", device_map="auto", load_in_4bit=True
... )

>>> model_inputs = tokenizer(["A sequence of numbers: 1, 2"], return_tensors="pt").to("cuda")
>>> # By default, the output will contain up to 20 tokens
>>> generated_ids = model.generate(**model_inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
'A sequence of numbers: 1, 2, 3, 4, 5'
>>> # Setting `max_new_tokens` allows you to control the maximum length
>>> generated_ids = model.generate(**model_inputs, max_new_tokens=50)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
'A sequence of numbers: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,'

>>> # Set seed or reproducibility -- you don't need this unless you want full reproducibility
>>> from transformers import set_seed
>>> set_seed(42)
>>> model_inputs = tokenizer(["I am a cat."], return_tensors="pt").to("cuda")
>>> # LLM + greedy decoding = repetitive, boring output
>>> generated_ids = model.generate(**model_inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
'I am a cat. I am a cat. I am a cat. I am a cat'
>>> # With sampling, the output becomes more creative!
>>> generated_ids = model.generate(**model_inputs, do_sample=True)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
'I am a cat.  Specifically, I am an indoor-only cat.  I'

>>> # The tokenizer initialized above has right-padding active by default: the 1st sequence,
>>> # which is shorter, has padding on the right side. Generation fails to capture the logic.
>>> model_inputs = tokenizer(
...     ["1, 2, 3", "A, B, C, D, E"], padding=True, return_tensors="pt"
... ).to("cuda")
>>> generated_ids = model.generate(**model_inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
'1, 2, 33333333333'
>>> # With left-padding, it works as expected!
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1", padding_side="left")
>>> tokenizer.pad_token = tokenizer.eos_token  # Most LLMs don't have a pad token by default
>>> model_inputs = tokenizer(
...     ["1, 2, 3", "A, B, C, D, E"], padding=True, return_tensors="pt"
... ).to("cuda")
>>> generated_ids = model.generate(**model_inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
'1, 2, 3, 4, 5, 6,'

>>> tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-alpha")
>>> model = AutoModelForCausalLM.from_pretrained(
...     "HuggingFaceH4/zephyr-7b-alpha", device_map="auto", load_in_4bit=True
... )
>>> set_seed(0)
>>> prompt = """How many helicopters can a human eat in one sitting? Reply as a thug."""
>>> model_inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
>>> input_length = model_inputs.input_ids.shape[1]
>>> generated_ids = model.generate(**model_inputs, max_new_tokens=20)
>>> print(tokenizer.batch_decode(generated_ids[:, input_length:], skip_special_tokens=True)[0])
"I'm not a thug, but i can tell you that a human cannot eat"
>>> # Oh no, it did not follow our instruction to reply as a thug! Let's see what happens when we write
>>> # a better prompt and use the right template for this model (through `tokenizer.apply_chat_template`)
>>> set_seed(0)
>>> messages = [
...     {
...         "role": "system",
...         "content": "You are a friendly chatbot who always responds in the style of a thug",
...     },
...     {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
... ]
>>> model_inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
>>> input_length = model_inputs.shape[1]
>>> generated_ids = model.generate(model_inputs, do_sample=True, max_new_tokens=20)
>>> print(tokenizer.batch_decode(generated_ids[:, input_length:], skip_special_tokens=True)[0])
'None, you thug. How bout you try to focus on more useful questions?'
>>> # As we can see, it followed a proper thug style 😎

pip install transformers datasets evaluate accelerate

>>> from huggingface_hub import notebook_login
>>> notebook_login()

>>> from datasets import load_dataset
>>> imdb = load_dataset("imdb")

>>> imdb["test"][0]
{
    "label": 0,
    "text": "I love sci-fi and am willing to put up with a lot. Sci-fi movies/TV are usually underfunded, under-appreciated and misunderstood. I tried to like this, I really did, but it is to good TV sci-fi as Babylon 5 is to Star Trek (the original). Silly prosthetics, cheap cardboard sets, stilted dialogues, CG that doesn't match the background, and painfully one-dimensional characters cannot be overcome with a 'sci-fi' setting. (I'm sure there are those of you out there who think Babylon 5 is good sci-fi TV. It's not. It's clichéd and uninspiring.) While US viewers might like emotion and character development, sci-fi is a genre that does not take itself seriously (cf. Star Trek). It may treat important issues, yet not as a serious philosophy. It's really difficult to care about the characters here as they are not simply foolish, just missing a spark of life. Their actions and reactions are wooden and predictable, often painful to watch. The makers of Earth KNOW it's rubbish as they have to always say \"Gene Roddenberry's Earth...\" otherwise people would not continue watching. Roddenberry's ashes must be turning in their orbit as this dull, cheap, poorly edited (watching it without advert breaks really brings this home) trudging Trabant of a show lumbers into space. Spoiler. So, kill off a main character. And then bring him back as another actor. Jeeez! Dallas all over again.",
}

>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")

>>> def preprocess_function(examples):
...     return tokenizer(examples["text"], truncation=True)

tokenized_imdb = imdb.map(preprocess_function, batched=True)

>>> from transformers import DataCollatorWithPadding
>>> data_collator = DataCollatorWithPadding(tokenizer=tokenizer)

>>> from transformers import DataCollatorWithPadding
>>> data_collator = DataCollatorWithPadding(tokenizer=tokenizer, return_tensors="tf")