Inference of LLaMA model in pure C/C++, The main goal of llama.cpp is to run the LLaMA model using 4-bit integer quantization on a MacBook.
数据统计
相关导航
暂无评论...
Inference of LLaMA model in pure C/C++, The main goal of llama.cpp is to run the LLaMA model using 4-bit integer quantization on a MacBook.