Update app.py

app.py

@@ -1,8 +1,8 @@
 from transformers import AutoModel, AutoTokenizer
 import gradio as gr
 
-tokenizer = AutoTokenizer.from_pretrained("anthonyfang/myllm3", trust_remote_code=True)
-model = AutoModel.from_pretrained("anthonyfang/myllm3", trust_remote_code=True).half()
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("anthonyfang/myllm3", trust_remote_code=True).quantize(bits=4, compile_parallel_kernel=True, parallel_num=2).cpu().float()
 model = model.eval()
 
 def predict(input, history=None):