Update app.py

app.py

@@ -3,18 +3,18 @@ from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
 
 model_path = "vinai/PhoGPT-7B5-Instruct"
 
-config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
+config = AutoConfig.from_pretrained(model_path, trust_remote_code=True, token='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')
 config.init_device = "cuda"
 # config.attn_config['attn_impl'] = 'triton' # Enable if "triton" installed!
 
 model = AutoModelForCausalLM.from_pretrained(
-    model_path, config=config, torch_dtype=torch.bfloat16, trust_remote_code=True
+    model_path, config=config, torch_dtype=torch.bfloat16, trust_remote_code=True, token='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'
 )
 # If your GPU does not support bfloat16:
 # model = AutoModelForCausalLM.from_pretrained(model_path, config=config, torch_dtype=torch.float16, trust_remote_code=True)
 model.eval()
 
-tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, token='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')
 
 
 def answer(input_prompt):