Update app.py

app.py

@@ -7,7 +7,7 @@ from transformers import AutoTokenizer
 # モデルとトークナイザーのロード
 model_name = "Sakalti/ultiima-78B-Q2-mlx"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = load(model_name, quantization="q2")
+model = load(model_name)
 
 def chat(prompt, top_p, top_k, max_new_tokens, system_prompt):
     messages = [