Update app.py

app.py

@@ -120,7 +120,7 @@ import transformers
 # model.half()
 
 MODEL_ID = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
-MODEL_ID = "microsoft/phi-4"
+# MODEL_ID = "microsoft/phi-4"
 
 CHAT_TEMPLATE = "َAuto"
 MODEL_NAME = MODEL_ID.split("/")[-1]
@@ -133,7 +133,7 @@ quantization_config = BitsAndBytesConfig(
     bnb_4bit_compute_dtype=torch.bfloat16
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
-model = AutoModelForCausalLM.from_pretrained(
+model = AutoModel.from_pretrained(
     MODEL_ID,
     device_map="auto",
      low_cpu_mem_usage=True,