Switch RAG generation model to Qwen2.5-7B-Instruct

services/rag_engine.py

@@ -16,7 +16,7 @@ K_RETRIEVE = 40
 K_FINAL = 8
 ALPHA = 0.05
 MAX_SNIPPET_CHARS = 280
-GEN_MODEL = "mistralai/Mistral-7B-Instruct-v0.3"
+GEN_MODEL = "Qwen/Qwen2.5-7B-Instruct"
 MAX_NEW_TOKENS = 400
 TEMPERATURE = 0.2
 TIMEOUT_SEC = 45