Update app.py

app.py

@@ -57,7 +57,7 @@ def get_llm():
     
     model = AutoModelForCausalLM.from_pretrained(
         LLM_MODEL,
-        cache_dir=CACHE_FOLDER,
+        #cache_dir=CACHE_FOLDER,
         device_map="auto",
         torch_dtype=torch.float16
     )