Debug记录：TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequen

问题

使用huggingfacetransformers库中tokenizer.encode()方法时遭遇报错：

TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]

报错代码

# 加载tokenizer
import torch
from transformers import AutoTokenizer
model_path = "J:\llm_model\meta-llama_Meta-Llama-3-8B"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

# 构建输入   
prompt_template = (
            "'instruction':'You are an expert in named entity recognition. "
                "Please extract entities from the input."
                "Return a empty list if the entity type does not exist."
                "Please respond in the format of a JSON string.', \n"
            "'input':'{text}' \n"
            "'result':")
data = [{
   "text":"iYqueCode为企业提供了一套高效、便捷的开箱即用的活码应用解决方案。"},
        {