Update app.py

app.py

@@ -49,6 +49,7 @@ device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'
 
 model_config = transformers.AutoConfig.from_pretrained(
             model_id,
+            token=HF_TOKEN,
             # use_auth_token=hf_auth
         )
 model = transformers.AutoModelForCausalLM.from_pretrained(
@@ -56,11 +57,13 @@ model = transformers.AutoModelForCausalLM.from_pretrained(
             trust_remote_code=True,
             config=model_config,
             quantization_config=bnb_config,
+            token=HF_TOKEN,
             # use_auth_token=hf_auth
         )
 model.eval()
 tokenizer = transformers.AutoTokenizer.from_pretrained(
             model_id,
+            token=HF_TOKEN,
             # use_auth_token=hf_auth
         )
 generate_text = transformers.pipeline(