Back to Details

transformers

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Transformers

Transformers

Overview

概述

The Hugging Face Transformers library provides access to thousands of pre-trained models for tasks across NLP, computer vision, audio, and multimodal domains. Use this skill to load models, perform inference, and fine-tune on custom data.
Hugging Face Transformers库提供了对数千个预训练模型的访问，这些模型适用于自然语言处理（NLP）、计算机视觉、音频和多模态领域的任务。使用此技能可以加载模型、执行推理并在自定义数据上进行微调。

Installation

安装

Install transformers and core dependencies:
bash
uv pip install torch transformers datasets evaluate accelerate
For vision tasks, add:
bash
uv pip install timm pillow
For audio tasks, add:
bash
uv pip install librosa soundfile
安装transformers及核心依赖：
bash
uv pip install torch transformers datasets evaluate accelerate
对于视觉任务，需额外安装：
bash
uv pip install timm pillow
对于音频任务，需额外安装：
bash
uv pip install librosa soundfile

Authentication

身份验证

Many models on the Hugging Face Hub require authentication. Set up access:
python
from huggingface_hub import login
login()  # Follow prompts to enter token
Or set environment variable:
bash
export HUGGINGFACE_TOKEN="your_token_here"
Get tokens at: https://huggingface.co/settings/tokens
Hugging Face Hub上的许多模型需要身份验证。请按以下步骤设置访问权限：
python
from huggingface_hub import login
login()  # Follow prompts to enter token
或者设置环境变量：
bash
export HUGGINGFACE_TOKEN="your_token_here"
获取令牌地址：https://huggingface.co/settings/tokens

Quick Start

快速开始

Use the Pipeline API for fast inference without manual configuration:
python
from transformers import pipeline
使用Pipeline API无需手动配置即可快速执行推理：
python
from transformers import pipeline

Text generation

Text generation

generator = pipeline("text-generation", model="gpt2") result = generator("The future of AI is", max_length=50)
generator = pipeline("text-generation", model="gpt2") result = generator("The future of AI is", max_length=50)

Text classification

Text classification

classifier = pipeline("text-classification") result = classifier("This movie was excellent!")
classifier = pipeline("text-classification") result = classifier("This movie was excellent!")

Question answering

Question answering

qa = pipeline("question-answering") result = qa(question="What is AI?", context="AI is artificial intelligence...")
undefined
qa = pipeline("question-answering") result = qa(question="What is AI?", context="AI is artificial intelligence...")
undefined

Core Capabilities

核心功能

1. Pipelines for Quick Inference

1. 快速推理管道

Use for simple, optimized inference across many tasks. Supports text generation, classification, NER, question answering, summarization, translation, image classification, object detection, audio classification, and more.
When to use: Quick prototyping, simple inference tasks, no custom preprocessing needed.
See 
references/pipelines.md
for comprehensive task coverage and optimization.
适用于多种任务的简单、优化推理。支持文本生成、分类、命名实体识别（NER）、问答、摘要、翻译、图像分类、目标检测、音频分类等。
适用场景：快速原型开发、简单推理任务、无需自定义预处理的场景。
有关全面的任务覆盖和优化，请参阅
references/pipelines.md
。

2. Model Loading and Management

2. 模型加载与管理

Load pre-trained models with fine-grained control over configuration, device placement, and precision.
When to use: Custom model initialization, advanced device management, model inspection.
See 
references/models.md
for loading patterns and best practices.
通过对配置、设备放置和精度的细粒度控制来加载预训练模型。
适用场景：自定义模型初始化、高级设备管理、模型检查。
有关加载模式和最佳实践，请参阅
references/models.md
。

3. Text Generation

3. 文本生成

Generate text with LLMs using various decoding strategies (greedy, beam search, sampling) and control parameters (temperature, top-k, top-p).
When to use: Creative text generation, code generation, conversational AI, text completion.
See 
references/generation.md
for generation strategies and parameters.
使用各种解码策略（贪心、束搜索、采样）和控制参数（temperature、top-k、top-p），通过大语言模型（LLM）生成文本。
适用场景：创意文本生成、代码生成、对话AI、文本补全。
有关生成策略和参数，请参阅
references/generation.md
。

4. Training and Fine-Tuning

4. 训练与微调

Fine-tune pre-trained models on custom datasets using the Trainer API with automatic mixed precision, distributed training, and logging.
When to use: Task-specific model adaptation, domain adaptation, improving model performance.
See 
references/training.md
for training workflows and best practices.
使用Trainer API在自定义数据集上微调预训练模型，支持自动混合精度、分布式训练和日志记录。
适用场景：任务特定模型适配、领域适配、提升模型性能。
有关训练工作流和最佳实践，请参阅
references/training.md
。

5. Tokenization

5. 分词

Convert text to tokens and token IDs for model input, with padding, truncation, and special token handling.
When to use: Custom preprocessing pipelines, understanding model inputs, batch processing.
See 
references/tokenizers.md
for tokenization details.
将文本转换为模型输入所需的令牌和令牌ID，支持填充、截断和特殊令牌处理。
适用场景：自定义预处理管道、理解模型输入、批量处理。
有关分词细节，请参阅
references/tokenizers.md
。

Common Patterns

常见模式

Pattern 1: Simple Inference

模式1：简单推理

For straightforward tasks, use pipelines:
python
pipe = pipeline("task-name", model="model-id")
output = pipe(input_data)
对于简单任务，使用管道：
python
pipe = pipeline("task-name", model="model-id")
output = pipe(input_data)

Pattern 2: Custom Model Usage

模式2：自定义模型使用

For advanced control, load model and tokenizer separately:
python
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("model-id")
model = AutoModelForCausalLM.from_pretrained("model-id", device_map="auto")

inputs = tokenizer("text", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
result = tokenizer.decode(outputs[0])
如需高级控制，分别加载模型和分词器：
python
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("model-id")
model = AutoModelForCausalLM.from_pretrained("model-id", device_map="auto")

inputs = tokenizer("text", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
result = tokenizer.decode(outputs[0])

Pattern 3: Fine-Tuning

模式3：微调

For task adaptation, use Trainer:
python
from transformers import Trainer, TrainingArguments

training_args = TrainingArguments(
    output_dir="./results",
    num_train_epochs=3,
    per_device_train_batch_size=8,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
)

trainer.train()
如需任务适配，使用Trainer：
python
from transformers import Trainer, TrainingArguments

training_args = TrainingArguments(
    output_dir="./results",
    num_train_epochs=3,
    per_device_train_batch_size=8,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
)

trainer.train()

Reference Documentation

参考文档

For detailed information on specific components:
  • Pipelines: 
    references/pipelines.md
    - All supported tasks and optimization
  • Models: 
    references/models.md
    - Loading, saving, and configuration
  • Generation: 
    references/generation.md
    - Text generation strategies and parameters
  • Training: 
    references/training.md
    - Fine-tuning with Trainer API
  • Tokenizers: 
    references/tokenizers.md
    - Tokenization and preprocessing
有关特定组件的详细信息：
  • 管道：
    references/pipelines.md
    - 所有支持的任务和优化
  • 模型：
    references/models.md
    - 加载、保存和配置
  • 生成：
    references/generation.md
    - 文本生成策略和参数
  • 训练：
    references/training.md
    - 使用Trainer API进行微调
  • 分词器：
    references/tokenizers.md
    - 分词和预处理