testChatGLM3 / app.py
kakuguo's picture
Update app.py
4170ee2
raw
history blame contribute delete
352 Bytes
import gradio as gr
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm3-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm3-6b", trust_remote_code=True).half().cuda()
model = model.eval()
response, history = model.chat(tokenizer, "δ½ ε₯½", history=[])
print(response)