trying to read token from the preset env

model.py

@@ -9,6 +9,7 @@ from huggingface_hub import login
 model_id = 'meta-llama/Llama-2-13b-chat-hf'
 
 if torch.cuda.is_available():
+    '''
     tok = os.environ['HF_TOKEN']
     login(new_session=True,
           write_permission=False,
@@ -16,7 +17,7 @@ if torch.cuda.is_available():
           
           #, token="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"
           )
-    
+    '''
     config = AutoConfig.from_pretrained(model_id,
         use_auth_token=True)
     config.pretraining_tp = 1
@@ -84,3 +85,8 @@ def run(message: str,
     for text in streamer:
         outputs.append(text)
         yield ''.join(outputs)
+
+'''
+raise gr.Error(f'The accumulated input is too long ({input_token_length} > {MAX_INPUT_TOKEN_LENGTH}). Clear your chat history and try again.')
+gradio.exceptions.Error: 'The accumulated input is too long (4191 > 4000). Clear your chat history and try again.'
+'''