Jimmy JIA comments

Results 5 comments of


                                            Jimmy JIA

RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

> 模型没真正克隆下来，怎么解决？可以去清华大学云盘手动下，然后替掉 [清华大学云盘](https://cloud.tsinghua.edu.cn/d/fb9f16d6dc8f482596c2/)

RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

> 我是用git lfs下载的模型文件目录，然后在清华云盘上下载的模型文件，导致ice_text.model不一致； > 用清华云盘上的ice_text.model替换之后就好了替换之后还是不行，有idea是怎么回事吗

有人知道怎么在python上调用llama2吗

可以参考 [reference huggingface](https://huggingface.co/FlagAlpha/Llama2-Chinese-13b-Chat/tree/main)

Is it still working? Trying to install but get an error...

@johnkree Hi. Have you solved this problem?

Failed to detect a default CUDA architecture

> CUDACXX=/usr/local/cuda-12/bin/nvcc CMAKE_ARGS="-DLLAMA_CUBLAS=on -DCMAKE_CUDA_ARCHITECTURES=native" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir --force-reinstall --upgrade thanks it works out in ubuntu22.4