Update app.py

app.py

@@ -64,7 +64,8 @@ def initialize_qa_chain(temperature, max_tokens, top_k, vector_db):
     
     llm = HuggingFaceEndpoint(
         # repo_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
-        repo_id="Qwen/Qwen2.5-1.5B-Instruct",
+        # repo_id="Qwen/Qwen2.5-1.5B-Instruct",
+        repo_id="google/gemma-2b-it",
         huggingfacehub_api_token=HF_TOKEN,  # Only needed if the model endpoint requires authentication
         temperature=temperature,
         max_new_tokens=max_tokens,
@@ -191,7 +192,8 @@ if not HF_TOKEN:
 # Global InferenceClient for plain chat (fallback)
 client = InferenceClient(
     # "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
-    "Qwen/Qwen2.5-1.5B-Instruct",
+    # "Qwen/Qwen2.5-1.5B-Instruct",
+    "google/gemma-2b-it",
     token=HF_TOKEN)
 
 # --- Auto-load vector database and initialize QA chain at startup ---