Can not deploy qwen2-vl

[wangzuohao]

System Info / 系統信息

Default docker latest images without any customization

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

• [X] docker / docker
• [ ] pip install / 通过 pip install 安装
• [ ] installation from source / 从源码安装

Version info / 版本信息

Latest version from docker image

The command used to start Xinference / 用以启动 xinference 的命令

docker run --name xinference -d -p 9997:9997 -e XINFERENCE_MODEL_SRC=modelscope -e XINFERENCE_HOME=/data -v /data:/data --gpus all xprobe/xinference:latest xinference-local -H 0.0.0.0

Reproduction / 复现过程

1, deploy the qwen2-vl models. 2. The issue happen for any model format and model size. 3. The error message is attached

Expected behavior / 期待表现

The model should be deployed without error

[kandada]

我也有同样的问题，怎么解决？ Server error: 500 - [address=0.0.0.0:35907, pid=2717359] cannot import name 'Qwen2VLForConditionalGeneration' from 'transformers'...

[goactiongo]

一样。 ImportError: [address=0.0.0.0:38381, pid=406] cannot import name 'Qwen2VLForConditionalGeneration' from 'transformers' (/usr/local/lib/python3.10/dist-packages/transformers/init.py)

[1234563536]

下载transformers-21fac7abba2a37fae86106f87fcf9974fd1e3830/ 然后pip install . 安装新版本的transformers即可

[github-actions[bot]]

This issue is stale because it has been open for 7 days with no activity.

[github-actions[bot]]

This issue was closed because it has been inactive for 5 days since being marked as stale.