Update app.py

app.py

@@ -18,12 +18,13 @@ if "HUGGINGFACEHUB_API_TOKEN" not in os.environ:
 
 # --- LLM and Template Configuration ---
 llm = HuggingFaceEndpoint(
-    repo_id="google/gemma-2b",
+    repo_id="HuggingFaceH4/zephyr-7b-alpha",  # inference-ready model
     temperature=0.7,
     max_new_tokens=512,
     huggingfacehub_api_token=os.getenv("HUGGINGFACEHUB_API_TOKEN"),
-    task="text2text-generation"
+    task="text-generation"   # <— important: use text-generation, not text2text-generation
 )
+
 math_template = ChatPromptTemplate.from_messages([
     ("system", """{system_message}
 You are an expert math tutor. For every math problem: