Embedder模型在容器中无法运行

[bookook]

基于intelanalytics/ipex-llm-xpu:latest镜像制作的镜像chatdoc_intel:1.1 启动容器test，无法加载Embedder模型。

dockerfile： FROM intelanalytics/ipex-llm-xpu:latest

RUN export DEBIAN_FRONTEND=noninteractive && \ sed -i s@/archive.ubuntu.com/@/mirrors.bfsu.edu.cn/@g /etc/apt/sources.list && \ rm -rf /etc/apt/sources.list.d/ && \ apt-get update && apt-get install -y --no-install-recommends \ curl \ ca-certificates && \ rm -rf /var/lib/apt/lists/*

RUN pip install --no-cache-dir --upgrade pip

RUN pip install --no-cache-dir --ignore-installed blinker

RUN pip install --no-cache-dir \ numpy \ transformers==4.37.0 \ tiktoken \ sentencepiece \ langchain \ dm-tree \ cachetools \ pandas \ pillow \ opencv-python-headless \ pyclipper \ shapely \ python-docx \ PyMuPDF \ pytz \ jieba \ nltk \ tenacity \ tqdm \ redis \ aiohttp \ fastapi \ uvicorn \ flask \ gunicorn \ pymilvus

WORKDIR /workspace

[liu-shaojun]

Hi @bookook Could you please provide your test script for loading the Embedder model? This will help us reproduce the process on our side. Thank you!

[liu-shaojun]

According to the sync in the WeChat group and with @bookook, we have resolved the error the user encountered.