Update app.py

app.py

@@ -28,7 +28,7 @@ model.eval()
 class GenerateRequest(BaseModel):
     prompt: str
     max_new_tokens: int = 512
-    temperature: float = 1.0
+    temperature: float = 0.7
 
 @app.post("/generate")
 async def generate_text(request: GenerateRequest):
@@ -41,6 +41,8 @@ async def generate_text(request: GenerateRequest):
                 max_new_tokens=request.max_new_tokens,
                 temperature=request.temperature,
                 do_sample=True,
+                top_p=0.95,
+                top_k=40,
                 pad_token_id=tokenizer.eos_token_id
             )