Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

为什么对于grounding任务没有使用带有think的system prompt #134

Open
zzzz123-0708 opened this issue Mar 8, 2025 · 1 comment

Comments

@zzzz123-0708
Copy link

我发现对于grounding任务没有使用带有think的system prompt,而是在user prompt后添加对于和的格式要求,这是什么原因,是因为效果不好吗,还是别的考虑,期待回复,感谢!

    # This is only for Grounding task
    QUESTION_TEMPLATE = "{Question} First output the thinking process in <think> </think> tags and then output the final answer in <answer> </answer> tags. Output the final answer in JSON format."
    def make_conversation_image(example):
        return {
            "prompt": [
                # {"role": "system", "content": [{"type": "text", "text": SYSTEM_PROMPT}]},
                {
                    "role": "user",
                    "content": [
                        {"type": "image"},
                        {"type": "text", "text": QUESTION_TEMPLATE.format(Question=example["problem"])},
                    ],
                },
            ],
        }
@SZhanZ
Copy link
Contributor

SZhanZ commented Mar 13, 2025

你好,当时简单看了一下前几个step的输出,对比下来感觉把“ ”的prompt加到问题后面会比直接加到system prompt里更好一些,所以就没有加system prompt。不过这个没有实验依据,而且对于不同种类,大小的模型结果可能都不一样,maybe需要具体的任务具体制定。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants