Update app.py

app.py

@@ -10,8 +10,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
-MODEL_ID = "nikravan/Marco_o1_q4"
-CHAT_TEMPLATE = "ChatML"
+MODEL_ID = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
+CHAT_TEMPLATE = "َAuto"
 MODEL_NAME = MODEL_ID.split("/")[-1]
 CONTEXT_LENGTH = 16000