Update app.py

app.py

@@ -12,7 +12,7 @@ key =  os.environ.get("key")
 from huggingface_hub import login 
 login(key)
 from bitnet import replace_linears_in_hf
-os.system("pip install flash-attn --no-build-isolation")
+# os.system("pip install flash-attn --no-build-isolation")
 nf4_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
@@ -25,7 +25,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id,
                                              # load_in_8bit=True,
                                              quantization_config=nf4_config,
-                                            attn_implementation="flash_attention_2",
+                                            # attn_implementation="flash_attention_2",
                                              # torch_dtype = torch.bfloat16,
                                              device_map="auto"
                                             )