prompt for Llava

[KansaiTraining]

In the llava.ipynb file you used

def create_prompt(prompt: str):
    conv = conv_templates[CONV_MODE].copy()
    roles = conv.roles
    prompt = DEFAULT_IMAGE_TOKEN + "\n" + prompt
    conv.append_message(roles[0], prompt)
    conv.append_message(roles[1], None)
    return conv.get_prompt(), conv

prompt, _ = create_prompt("Describe the image")
print(prompt)

To create a prompt with the CONV_MODE being llava_v0

is this official? When querying llava models should we use this prompt format

A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: <image>
Describe the image###Assistant: