Update app.py

app.py

@@ -33,8 +33,8 @@ def load_pipeline():
     index.add(kb_embeddings)
     
     # 3. Load Generative LLM (CPU mode)
-    llama_tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
-    llama_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct", device_map="cpu")
+    llama_tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
+    llama_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct", device_map="cpu")
     
     return distil_tokenizer, distil_model, kb, embedder, index, llama_tokenizer, llama_model