How to ask proper question for AutoTrained LLM ?

[charles-123456]

Hi,
If I follow the below sample not answer any question:

rom transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "catai_bert-base-uncased_finetuning"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="cuda",
torch_dtype='auto'
).eval()

Prompt content: "hi"

messages = [
{"role": "user", "content": "hi"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

Model response: "Hello! How can I assist you today?"

print(response)