下载glm4-chat时，选择8-bit，下载报错Server error: 500 - [address=127.0.0.1:4389, pid=15108] 'transfomg.word_embeddings.weight'

[MrTLin]

System Info / 系統信息

Cuda:12.1
transformens:4.46.1
python:3.10
操作系统：windows 11
显卡：3090

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

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

Version info / 版本信息

V.0.16.2

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

1.pip install "xinference[transformers]"
2.xinference-local

Reproduction / 复现过程

1.pip install "xinference[transformers]"
2.xinference-local
3.浏览器打开http://localhost:9997
4.拉取glm4-chat，Engine选择transformers，quantization选择8-bit

Expected behavior / 期待表现

如何解决这个问题:下载glm4-chat时，选择8-bit，下载报错：Server error: 500 - [address=127.0.0.1:4389, pid=15108] 'transfomg.word_embeddings.weight'

[github-actions]

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