Update app.py

app.py

@@ -22,6 +22,7 @@ peft_model_id = "Imran1/Llama3.1_8b_Dora"
  #attn_implementation="flash_attention_2",
 model = AutoModelForCausalLM.from_pretrained(model_id, attn_implementation="sdpa",  torch_dtype= torch.bfloat16)
 model.load_adapter(peft_model_id)
+model.enable_adapters()
 tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
 # streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 model.to('cuda')