昇思25天学习打卡营第22天|MindNLP ChatGLM-6B StreamChat

基于MindNLP和ChatGLM-6B实现一个聊天应用

1.环境配置

pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.2.14

# 配置网络线路
pip install mdtex2html
pip install mindnlp

2.镜像模型下载

下载模型，加载模型，测试应用聊天

from mindnlp.transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import gradio as gr
import mdtex2html

model = AutoModelForSeq2SeqLM.from_pretrained('ZhipuAI/ChatGLM-6B', mirror="modelscope").half()
model.set_train(False)
tokenizer = AutoTokenizer.from_pretrained('ZhipuAI/ChatGLM-6B', mirror="modelscope")

prompt = '你好'
history = []
response, _ = model.chat(tokenizer, prompt, history=history, max_length=20)
print(response)