add app.py int4 cpu model and stream show

app.py

@@ -2,12 +2,8 @@ from transformers import AutoModel, AutoTokenizer
 import gradio as gr
 import mdtex2html
 
-<<<<<<< HEAD
-# tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
-# model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
 tokenizer = AutoTokenizer.from_pretrained("models/chatglm-6b-int4", trust_remote_code=True, revision="")
 model = AutoModel.from_pretrained("models/chatglm-6b-int4", trust_remote_code=True, revision="").float()
-=======
 # tokenizer = AutoTokenizer.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="")
 # model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda()
 # chatglm-6b-int4 cuda，本地可以运行成功
@@ -16,8 +12,8 @@ model = AutoModel.from_pretrained("models/chatglm-6b-int4", trust_remote_code=Tr
 
 
 # chatglm-6b-int4 CPU，
-tokenizer = AutoTokenizer.from_pretrained("models/chatglm-6b-int4", trust_remote_code=True, revision="")
-model = AutoModel.from_pretrained("models/chatglm-6b-int4", trust_remote_code=True, revision="").float()
+# tokenizer = AutoTokenizer.from_pretrained("models/chatglm-6b-int4", trust_remote_code=True, revision="")
+# model = AutoModel.from_pretrained("models/chatglm-6b-int4", trust_remote_code=True, revision="").float()
 
 
 
@@ -29,9 +25,6 @@ model = AutoModel.from_pretrained("models/chatglm-6b-int4", trust_remote_code=Tr
 
 
 
-# model = model.quantize(bits=model_args.quantization_bit, kernel_file=kernel_file)
->>>>>>> a5ffac38caa4a817f0c1633254d42160662806a8
-
 model = model.eval()
 
 """Override Chatbot.postprocess"""