You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.
3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
This issue is marked as stale because it has been marked as invalid or awaiting response for 7 days without any further response. It will be closed in 5 days if the stale label is not removed or if there is no further response.
Checklist
Describe the bug
我使用lmdeploy部署了qwen-vl。输入遵循openai的vision格式,但是一个role会有两段text,如:
"messages"= [
{
"content": [
{
"type": "text",
"text": "你好"
},
{
"image_url": {
"url": "{{url}}"
},
"type": "image_url"
},
{
"type": "text",
"text": "描述一下这个图片"
}
],
"role": "user"
}]
但是后端拼接的结果长这样:
把第一段的"你好"给吞掉了。
查阅了相关源码,发现构造 vision message的时候会最后一个text会覆盖之前的text。
请问这个现象是正常的吗,能修复吗?
Reproduction
Environment
Error traceback
No response
The text was updated successfully, but these errors were encountered: