Skip to content

error loading model: unknown model architecture: ‘qwen2‘ #92

@huaihkiss

Description

@huaihkiss

llama_cpp_python不支持qwen2,需要更新,需要按照cuda版本更新,如果没有按照cuda版本更新可能会不使用显卡

`
#卸载原有
pip uninstall llama-cpp-python
#安装新版,cuda-version为cu121、cu122、cu123、cu124,python版本仅支持3.10、3.11、3.12
pip install llama-cpp-python
--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/

#假设为cuda 12.1

pip install llama-cpp-python
--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121
`

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions