Update app.py

app.py

@@ -3,9 +3,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
 app = FastAPI()
 
-# 🚀 さらに軽いモデルを選択（7B → 3.6B）
+# 🚀 軽量な日本語モデルを選択（7B → 3.6B）
 MODEL_NAME = "rinna/japanese-gpt-neox-3.6b"
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=False)
 model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
 generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
@@ -17,3 +17,4 @@ def root():
 def generate(prompt: str, max_length: int = 100):
     result = generator(prompt, max_length=max_length, do_sample=True)[0]['generated_text']
     return {"response": result}
+