大型语言模型的国际合作与竞争

    from transformers import BertTokenizer, BertForSequenceClassification
    import torch
    
    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
    model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
    
    inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
    labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
    outputs = model(**inputs, labels=labels)
    loss = outputs.loss
    logits = outputs.logits
    
      
      
      
      
      
      
      
      
      
      
    
    代码解读

    from transformers import BertTokenizer, BertForSequenceClassification, Trainer, TrainingArguments
    import torch
    import numpy as np
    
    # Load dataset
    train_texts, train_labels = ...
    val_texts, val_labels = ...
    
    # Tokenize dataset
    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
    train_encodings = tokenizer(train_texts, truncation=True, padding=True)
    val_encodings = tokenizer(val_texts, truncation=True, padding=True)
    
    # Create dataset
    class TextDataset(torch.utils.data.Dataset):
    def __init__(self, encodings, labels):
        self.encodings = encodings
        self.labels = labels
    
    def __getitem__(self, idx):
        item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
        item['labels'] = torch.tensor(self.labels[idx])
        return item
    
    def __len__(self):
        return len(self.labels)
    
    train_dataset = TextDataset(train_encodings, train_labels)
    val_dataset = TextDataset(val_encodings, val_labels)
    
    # Fine-tune model
    model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
    training_args = TrainingArguments(
    output_dir='./results',          # output directory
    num_train_epochs=3,              # total number of training epochs
    per_device_train_batch_size=16,  # batch size per device during training
    per_device_eval_batch_size=64,   # batch size for evaluation
    warmup_steps=500,                # number of warmup steps for learning rate scheduler
    weight_decay=0.01,               # strength of weight decay
    logging_dir='./logs',            # directory for storing logs
    )
    
    trainer = Trainer(
    model=model,                         # the instantiated 🤗 Transformers model to be trained
    args=training_args,                  # training arguments, defined above
    train_dataset=train_dataset,         # training dataset
    eval_dataset=val_dataset             # evaluation dataset
    )
    
    trainer.train()
    
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
    代码解读