Update app.py

app.py

@@ -34,7 +34,7 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
-    model_id = "deepseek-ai/DeepSeek-V2-Lite-Chat"
+    model_id = "AI-MO/NuminaMath-7B-TIR"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False
@@ -46,7 +46,7 @@ def generate(
     message: str,
     chat_history: list[tuple[str, str]],
     system_prompt: str,
-    max_new_tokens: int = 1024,
+    max_new_tokens: int = 2048,
     temperature: float = 0.6,
     top_p: float = 0.9,
     top_k: int = 50,