Update app.py

app.py

@@ -20,7 +20,7 @@ max_new_tokens = 3000
 top_p = 0.95
 repetition_penalty = 1.2
 
-model_name = "PleIAs/Cassandre-RAG"
+model_name = "PleIAs/llama-reasoning-rag"
 
 # Initialize vLLM
 llm = LLM(model_name, max_model_len=8128)