Best practice for training LLaMA models in Megatron-LM

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Quick Start LLaMA models with multiple methods, and fine-tune 7B/65B with One-Click.

This repository is an example on how to structure you python project.

Unofficial maintenance repository of Torch7. It supports CUDA10.1, Volta, Turing, Docker https://hub.docker.com/r/nagadomi/torch7

ncnn is a high-performance neural network inference framework optimized for the mobile platform