using now TheBloke/Falcon-180B-Chat-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/alpaca-lora-65B-GPTQ")
+    tokenizer = AutoTokenizer.from_pretrained("TheBloke/Falcon-180B-Chat-GPTQ")
     model = AutoModelForCausalLM.from_pretrained(
         "TheBloke/Mistral-7B-Instruct-v0.2-AWQ",
         device_map="auto",
@@ -25,9 +25,9 @@ except Exception as e:
     try:
         # Second try: Use a smaller, more compatible model
         print("🔄 Falling back to Mistral-7B-Instruct-v0.1 (more compatible)...")
-        tokenizer = AutoTokenizer.from_pretrained("TheBloke/alpaca-lora-65B-GPTQ")
+        tokenizer = AutoTokenizer.from_pretrained("TheBloke/Falcon-180B-Chat-GPTQ")
         model = AutoModelForCausalLM.from_pretrained(
-            "TheBloke/alpaca-lora-65B-GPTQ",
+            "TheBloke/Falcon-180B-Chat-GPTQ",
             device_map="auto",
             torch_dtype=torch.float16,
             low_cpu_mem_usage=True,