Update app.py

app.py

@@ -26,7 +26,7 @@ def load_model_norm():
     model_name_or_path = "TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ"
     # To use a different branch, change revision
     # For example: revision="main"
-    model = AutoModelForCausalLM.from_pretrained(model_name_or_path,device_map="auto", trust_remote_code=True,revision="gptq-4bit-128g-actorder_True")
+    model = AutoModelForCausalLM.from_pretrained(model_name_or_path,device_map="auto", trust_remote_code=True,revision="main")
     # Switch to CPU inference
     #model.to("cuda")
     tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)