Update app.py

app.py

@@ -13,7 +13,7 @@ model_name = "EpistemeAI/Episteme-gptoss-20b-RL"
 print(f"Loading model: {model_name}")
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_name=model_name,
-    load_in_4bit=True,
+    load_in_4bit=False,
     dtype=None,
     device_map="auto",
 )