【NLP】32. Transformers (HuggingFace Pipelines 实战)

🤖 Transformers (HuggingFace Pipelines 实战)

本教程基于 Hugging Face 的 transformers 库,展示如何使用预训练模型完成以下任务:

  • 情感分析(Sentiment Analysis)
  • 文本生成(Text Generation)
  • 翻译(Translation)
  • 掩码填空(Masked Language Modeling)
  • 零样本分类(Zero-shot Classification)
  • 特定任务模型推理(Text2Text Generation, e.g., T5)
  • 文本摘要(Summarization)
  • 自定义分类模型载入与推理(如 BERT)

📦 安装依赖

python 复制代码
!pip install datasets evaluate transformers sentencepiece -q

✅ 情感分析

python 复制代码
from transformers import pipeline

classifier = pipeline("sentiment-analysis")

# 单个句子
classifier("I really enjoy learning new things every day.")

# 多个句子
classifier([
    "I really enjoy learning new things every day.",
    "I dislike rainy weather on weekends."
])

✍️ 文本生成(默认模型)

python 复制代码
from transformers import pipeline

generator = pipeline("text-generation")
generator("Today we are going to explore something exciting")

🎯 文本生成(指定参数)

python 复制代码
# 两句话,每句最多15词
generator("Today we are going to explore something exciting", num_return_sequences=2, max_length=15)

⚙️ 使用 distilgpt2 模型生成文本

python 复制代码
from transformers import pipeline

generator = pipeline("text-generation", model="distilgpt2")
generator(
    "Today we are going to explore something exciting",
    max_length=30,
    num_return_sequences=2,
)

🌍 翻译(英语→德语)

python 复制代码
from transformers import pipeline

translator = pipeline("translation_en_to_de")
translator("This is a great day to learn something new!")

🧩 掩码填空任务(填词)

python 复制代码
from transformers import pipeline

unmasker = pipeline("fill-mask")
unmasker("Life is like a <mask> of chocolates.")

🧠 零样本分类(Zero-shot Classification)

python 复制代码
from transformers import pipeline

classifier = pipeline("zero-shot-classification")
classifier(
    "This tutorial is about machine learning and natural language processing.",
    candidate_labels=["education", "sports", "politics"]
)

🔁 T5 模型(Text2Text)

python 复制代码
from transformers import pipeline

text2text = pipeline("text2text-generation")
text2text("Translate English to French: How are you today?")

✂️ 文本摘要(Summarization)

python 复制代码
from transformers import pipeline

summarizer = pipeline("summarization")
summarizer(
    "Machine learning is a field of artificial intelligence that focuses on enabling machines to learn from data..."
)

🧪 使用自己的模型(以 BERT 为例)

python 复制代码
from transformers import BertTokenizer, BertForSequenceClassification
from transformers import pipeline

model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
tokenizer = BertTokenizer.from_pretrained(model_name)
model = BertForSequenceClassification.from_pretrained(model_name)

pipe = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
pipe("I had an amazing experience with this product!")
相关推荐
盘古信息IMS20 分钟前
告别 “老系统困境”!三真科技 × 盘古信息:汽车电子数字化工厂升级
人工智能·科技·汽车
Alter123025 分钟前
用AI重构人机关系,OPPO智慧服务带来了更“懂你”的体验
人工智能·重构
爱看科技25 分钟前
科技新突破!微美全息(NASDAQ:WIMI)研发保留运动想象脑机接口“方差密钥”技术
大数据·人工智能·科技
中科岩创34 分钟前
青海某公路水渠自动化监测服务项目
大数据·人工智能·物联网
报错小能手40 分钟前
python(入门)map内置函数及import模块导入,as别名
开发语言·人工智能·python
Jump 不二1 小时前
百度 PaddleOCR 3.0 深度测评:与 MinerU 的复杂表格识别对决
人工智能·深度学习·百度·ocr
用户5191495848451 小时前
Flutter应用设置插件 - 轻松打开iOS和Android系统设置
人工智能·aigc
孤廖1 小时前
C++ 模板再升级:非类型参数、特化技巧(含全特化与偏特化)、分离编译破解
linux·服务器·开发语言·c++·人工智能·后端·深度学习
润 下1 小时前
C语言——回调函数的典型示例(分析详解)
c语言·开发语言·人工智能·经验分享·笔记·程序人生