Update app.py

app.py

@@ -7,7 +7,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 import torch
 import os
 import bitnet
-
+os.system('pip install mamba-ssm causal-conv1d>=1.2.0')
 key =  os.environ.get("key")
 from huggingface_hub import login 
 login(key)
@@ -28,7 +28,8 @@ model = AutoModelForCausalLM.from_pretrained(model_id,
                                              quantization_config=nf4_config,
                                             # attn_implementation="flash_attention_2",
                                              # torch_dtype = torch.bfloat16,
-                                             device_map="auto"
+                                             device_map="auto",
+                                             trust_remote_code=True
                                             )
 
 # replace_linears_in_hf(model)