PKU-Alignment/alpaca-7b-reproduced

PKU-Alignment/alpaca-7b-reproduced is a 7 billion parameter instruction-following language model developed by the PKU-Alignment Team, fine-tuned from the LLaMA foundation model. This version is a reproduction of Stanford Alpaca, utilizing the DeepSpeed library for training and featuring a distinct conversation template. It is designed for general instruction-following tasks, offering a non-commercial license.