changed model

app.py

@@ -4,8 +4,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-13b-chat-hf",trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-13b-chat-hf", trust_remote_code=True).float()
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True).float()
 
 
 def chat(message,history):