pip install bert4pytorch==0.1.2

from bert4pytorch.modeling import BertModel, BertConfig
from bert4pytorch.tokenization import BertTokenizer
from bert4pytorch.optimization import AdamW, get_linear_schedule_with_warmup
import torch

model_path = "/model/pytorch_bert_pretrain_model"
config = BertConfig(model_path + "/config.json")

tokenizer = BertTokenizer(model_path + "/vocab.txt")
model = BertModel.from_pretrained(model_path, config)

input_ids, token_type_ids = tokenizer.encode("今天很开心")

input_ids = torch.tensor([input_ids])
token_type_ids = torch.tensor([token_type_ids])

model.eval()

outputs = model(input_ids, token_type_ids, output_all_encoded_layers=True)

## orther code

param_optimizer = list(model.named_parameters())
no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight']
optimizer_grouped_parameters = [
    {'params': [p for n, p in param_optimizer
                if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01},
    {'params': [p for n, p in param_optimizer
                if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}
]
optimizer = AdamW(optimizer_grouped_parameters, lr=1e-5, correct_bias=False)

num_training_steps=train_batches * num_epoches
num_warmup_steps=num_training_steps * warmup_proportion
schedule = get_linear_schedule_with_warmup(optimizer, num_warmup_steps, num_training_steps)