Update app/llm.py

app/llm.py

@@ -114,7 +114,7 @@ async def generate(gen:GenModel):#, user: schemas.BaseUser = fastapi.Depends(cur
             seed= gen.seed,
             #chat_format="llama-2",
             stream=True,
-            echo = not True
+            echo = True
         )
         
         for chunk in output:
@@ -128,7 +128,7 @@ async def generate(gen:GenModel):#, user: schemas.BaseUser = fastapi.Depends(cur
         
         #et = time()
         #output["time"] = et - st
-        print(output)
+        #print(output)
     except Exception as e:
         logger.error(f"Error in /generate endpoint: {e}")
         return JSONResponse(