大语言模型（LLM）入门指南与核心技术解析

前言

import torch from torch import nn, optim from torchvision import datasets, transforms from torch.utils.data import DataLoader # 定义数据预处理 transform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,)) ]) # 加载 FashionMNIST 数据集 train_dataset = datasets.FashionMNIST(root='./data', train=True, download=True, transform=transform) test_dataset = datasets.FashionMNIST(root='./data', train=False, download=True, transform=transform) # 创建数据加载器 train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True) test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False) # 定义神经网络结构 class FashionMNISTNN(nn.Module): def __init__(self): super(FashionMNISTNN, self).__init__() self.flatten = nn.Flatten() self.linear_relu_stack = nn.Sequential( nn.Linear(28*28, 512), nn.ReLU(), nn.Linear(512, 256), nn.ReLU(), nn.Linear(256, 10), ) def forward(self, x): x = self.flatten(x) logits = self.linear_relu_stack(x) return logits model = FashionMNISTNN() # 定义损失函数和优化器 loss_fn = nn.CrossEntropyLoss() optimizer = optim.Adam(model.parameters(), lr=0.001) # 训练函数 def train(dataloader, model, loss_fn, optimizer): size = len(dataloader.dataset) model.train() for batch, (X, y) in enumerate(dataloader): pred = model(X) loss = loss_fn(pred, y) optimizer.zero_grad() loss.backward() optimizer.step() if batch % 100 == 0: loss_val, current = loss.item(), batch * len(X) print(f"loss: {loss_val:>7f} [{current:>5d}/{size:>5d}]") # 测试函数 def test(dataloader, model, loss_fn): size = len(dataloader.dataset) num_batches = len(dataloader) model.eval() test_loss, correct = 0, 0 with torch.no_grad(): for X, y in dataloader: pred = model(X) test_loss += loss_fn(pred, y).item() correct += (pred.argmax(1) == y).type(torch.float).sum().item() test_loss /= num_batches correct /= size print(f"Test Error: Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f}") # 开始训练 epochs = 5 for t in range(epochs): print(f"Epoch {t+1}\n-------------------------------") train(train_loader, model, loss_fn, optimizer) test(test_loader, model, loss_fn) print("Done!")

大语言模型（LLM）入门指南与核心技术解析