本地部署bert-base-chinese模型交互式问答，gradio

最新推荐文章于 2025-04-14 16:53:47 发布

raoxiaoya

最新推荐文章于 2025-04-14 16:53:47 发布

阅读量703

点赞数 3

分类专栏：人工智能文章标签： bert 人工智能深度学习

本文链接：https://blog.youkuaiyun.com/raoxiaoya/article/details/143398030

版权

首先下载bert-base-chinese，可以在 Huggingface, modelscope, github下载

pip install gradio torch transformers

import gradio as gr
import torch
from transformers import BertTokenizer, BertForQuestionAnswering

# 加载bert-base-chinese模型和分词器
model_name = "D:/dev/php/magook/trunk/server/learn-python/models/bert-base-chinese"
tokenizer = BertTokenizer.from_pretrained(model_name)
model = BertForQuestionAnswering