llama_cpp_python运行Qwen2提示error loading model: unknown model architecture: ‘qwen2‘_error: exception error loading model architecture:

作者：小惠珠哦 | 2024-07-19 10:51:56

踩

error: exception error loading model architecture: unknown model architectur

llama_cpp_python版本不支持qwen2导致，可以更新到新版


#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
CMAKE_ARGS="-DLLAMA_CUDA=on -DLLAMA_CUBLAS=on" pip install llama-cpp-python \
  --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/<cuda-version>
 
#假设为cuda 12.1
 
CMAKE_ARGS="-DLLAMA_CUDA=on -DLLAMA_CUBLAS=on" pip install llama-cpp-python \
  --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121

本文内容由网友自发贡献，转载请注明出处：https://www.wpsshop.cn/w/小惠珠哦/article/detail/851067