search

harrisonvanderbyl / rwkv-cpp-accelerated

A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependencies
MIT License
306 stars 19 forks source link

fail to load on windows #27

Open flizzywine opened 1 year ago

flizzywine commented 1 year ago

Try to load model, but failed. Below is the output.

D:\AI\ChatRWKV\rwkv-cpp-cuda> chat.exe
D:\AI\ChatRWKV\rwkv-cpp-cuda/model.bin
n_layers: 431231561062       
n_embed: 17592186094693      
loading: xbuf

Windows use "\" as delimiter, but the rwkv.cpp use "/" as delimiter. And the model path being D:\AI\ChatRWKV\rwkv-cpp-cuda/model.bin is not correct. Want help, Thanks.

harrisonvanderbyl commented 1 year ago

This is loading a model, but the model file is not correct. Did you convert a model or did you download a preconverted file?

flizzywine commented 1 year ago

Thanks. I download a preconverted model. but not the english version. so I think that's the cause