wencan
@LiJianmin6706 活人？？如果是生成的，请加标注，减少不必要的污染
@SigureMo install ``` 'git+https://github.com/huggingface/safetensors.git#subdirectory=bindings/python' ```之后 报错是： ``` /home/wencan/Projects/venv/paddleocr/lib/python3.13/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from:...
> > > > > 目前需要使用特殊版本的safetensors加载模型，请参考文档中的说明安装～ > > > > > > > > > > > > [@Bobholamovic](https://github.com/Bobholamovic) 你好，这个 https://paddle-whl.bj.bcebos.com/nightly/cu126/safetensors/safetensors-0.6.2.dev0-cp38-abi3-linux_x86_64.whl 可以提供一下windows平台（win_amd64）的whl吗？ > > > > > > > >...
@keyboard3 如果出现把每行当作每段，间距紧凑又无法解决的情况，应该怎么处理？
@justinfagnani The lit-core package can meet the needs of most users. https://cdn.jsdelivr.net/gh/lit/[email protected]/core/
I compiled the llama.cpp file with version [b2636](https://github.com/ggerganov/llama.cpp/releases/tag/b2636), successfully converted sensenova/piccolo-base-zh to gguf format, and quantized it to Q4_K-M format.
@mlomeli1 I have always used pip + venv. This combination has always worked well.