The inference output is meaningless

When i input an image , the inference output is repetitive and not well-organized.

`conversation = [
{
"role": "<|User|>",
"content": "\n Describe the image.",
"images": ["../data/cat.png"],
},
{"role": "<|Assistant|>", "content": ""},
]

pil_images = load_pil_images(conversation)
prepare_inputs = vl_chat_processor(conversations=conversation, images=pil_images, force_batchify=True, system_prompt="Describe the image.").to(vl_gpt.device)
inputs_embeds = vl_gpt.prepare_inputs_embeds(**prepare_inputs)

outputs = vl_gpt.language.generate(
inputs_embeds=inputs_embeds,
attention_mask=prepare_inputs.attention_mask,
pad_token_id=tokenizer.eos_token_id,
bos_token_id=tokenizer.bos_token_id,
eos_token_id=tokenizer.eos_token_id,
max_new_tokens=128,
do_sample=False,
use_cache=True
)

answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=True)
print(f"{prepare_inputs['sft_format'][0]}", answer)`

The output is follow:
Describe the image.

<|User|>:
Describe the image.

<|Assistant|>: The image shows a cat wearing a shirt with a shirt with a design that resembles a shirt with a design that resembles a shirt with a design that resembles a shirt with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with with