Distribute and run LLMs with a single file.

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

llama and other large language models on iOS and MacOS offline using GGML library.

Extend the original llama.cpp repo to support redpajama model.

Dart wrapper via dart:ffi for https://github.com/twain/twain-dsm

Port of Facebook's LLaMA model in C/C++