Update app.py

app.py

@@ -69,6 +69,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id, token= token,
                                              # #  # torch_dtype=torch.fl,
                                              attn_implementation="flash_attention_2",
                                              low_cpu_mem_usage=True,
+                                             trust_remote_code=True,
                                              # device_map='cuda',
                                              # device_map=accelerator.device_map,