Update app.py

app.py

@@ -36,12 +36,12 @@ try:
     print("🔄 Loading tokenizer and model...")
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForCausalLM.from_pretrained(
-        model_name,
-        torch_dtype=torch.float16,
-        trust_remote_code=True,
-        device_map="auto",
-        low_cpu_mem_usage=True
-    )
+    MODEL_NAME_PRIMARY,
+    torch_dtype=torch.float16,
+    trust_remote_code=True,
+    device_map="auto",
+    low_cpu_mem_usage=True
+)
 
     generator = pipeline(
         "text-generation",