Update llm.py

llm.py

@@ -8,7 +8,8 @@ from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
 text_generator = pipeline(
     "text-generation",  # Task type
     model="google/gemma-3n-e4b-it",
-    device="cuda" if torch.cuda.is_available() else "cpu",
+    # device="cuda" if torch.cuda.is_available() else "cpu",
+    device= "cpu",,
     torch_dtype=torch.bfloat16,
     max_new_tokens=500  # Limit output length
 )