Update app.py

app.py

@@ -8,7 +8,7 @@ from transformers import (AutoModelForCausalLM, AutoTokenizer, LlamaForCausalLM,
 app = FastAPI()
     
 # Load the model and tokenizer
-model_name_or_path = "TheBloke/Wizard-Vicuna-7B-Uncensored-GPT/"
+model_name_or_path = "TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ"
 # Dictionary to store conversation threads and their context
 conversations = {}
 Device_Type = "cuda"