Update app.py

app.py

@@ -10,7 +10,7 @@ from threading import Thread
 # Load model directly
 device = "cuda" if torch.cuda.is_available() else "cpu"
 tokenizer = AutoTokenizer.from_pretrained("Navid-AI/Mulhem-1-Mini", token=os.getenv("HF_TOKEN"))
-model = AutoModelForCausalLM.from_pretrained("Navid-AI/Mulhem-1-Mini", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2", token=os.getenv("HF_TOKEN")).to(device)
+model = AutoModelForCausalLM.from_pretrained("Navid-AI/Mulhem-1-Mini", torch_dtype=torch.bfloat16, token=os.getenv("HF_TOKEN")).to(device)
 streamer = TextIteratorStreamer(tokenizer, skip_prompt=True)
 
 def respond(