trying to use TheBloke/alpaca-lora-65B-GPTQ

app.py

@@ -10,7 +10,7 @@ print("Loading optimized Mistral model...")
 try:
     # First try: AWQ quantized model (best performance)
     print("🔄 Attempting to load AWQ model...")
-    tokenizer = AutoTokenizer.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.2-AWQ")
+    tokenizer = AutoTokenizer.from_pretrained("TheBloke/alpaca-lora-65B-GPTQ")
     model = AutoModelForCausalLM.from_pretrained(
         "TheBloke/Mistral-7B-Instruct-v0.2-AWQ",
         device_map="auto",