帮我用bert和pytorch等价实现nn.Embedding.from_pretrained()

当使用BERT和PyTorch时，可以使用以下代码实现nn.Embedding.from_pretrained()的等效功能：

import torch
from transformers import BertModel

# Load pre-trained BERT model
model = BertModel.from_pretrained('bert-base-uncased')

# Get the embedding weights from the BERT model
embedding_weights = model.embeddings.word_embeddings.weight

# Create an nn.Embedding layer with the pre-trained weights
embedding_layer = torch.nn.Embedding.from_pretrained(embedding_weights)

这将使用BERT模型中的预训练权重创建一个nn.Embedding层。