fixing load bug

app.py

@@ -8,10 +8,17 @@ from config import config
 model_name = "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ"
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
 
-model = AutoModelForCausalLM.from_pretrained(config["model_checkpoint"],
-                                                device_map="auto",
-                                                trust_remote_code=False,
-                                                revision="main")
+print("model start loading")
+model = AutoModelForCausalLM.from_pretrained(model_name,
+                                             device_map="auto",
+                                             trust_remote_code=False,
+                                             revision="main")
+print("model loaded")
+
+# model = AutoModelForCausalLM.from_pretrained(config["model_checkpoint"],
+#                                                 device_map="auto",
+#                                                 trust_remote_code=False,
+#                                                 revision="main")
 
 
 def respond(