[BUG] <title>请问微调的时候图片描述的默认prompt是什么 - Githubissues

QwenLM / Qwen-VL

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Other

4.76k stars 359 forks source link

[BUG] <title>请问微调的时候图片描述的默认prompt是什么 #298

Open delltower opened 6 months ago

delltower commented 6 months ago

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

[X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

[X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

正在用数据微调模型，让模型输出图片的描述，请问Qwen-VL训练的时候，关于图片描述的任务的prompt是什么，我想和原来的模型对齐

期望行为 | Expected Behavior

正在用数据微调模型，让模型输出图片的描述，请问Qwen-VL训练的时候，关于图片描述的任务的prompt是什么，我想和原来的模型对齐

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):

备注 | Anything else?

No response

liuhuan-gl commented 3 months ago

请问解决了吗，我也遇到同样的问题，谢谢