Chinese LLaMA & Alpaca LLMs

Recently, there has been an increasing interest in the field of natural language processing due to the development of Large Language Models (LLM), such as ChatGPT, GPT-4, etc. LLM has shown its potential in achieving general artificial intelligence (AGI). However, the resource-consuming nature of these models has posed certain challenges to the open academic research.

This project focuses on:

• ? Enhancing the Chinese vocabulary of the original LLaMA model, improving the efficiency of Chinese encoding and decoding
• ? Making the Chinese LLaMA large model (7B, 13B) pre-trained using Chinese text data open source
• ? Making the Chinese Alpaca large model (7B, 13B) that has been further fine-tuned by instructions open source
• ? Enabling people to deploy the quantized version of the model locally, and experience it on their laptop (personal PC)
• ? The image below illustrates the actual experience after the localized deployment of the 7B version model (animation is not accelerated, measured on Apple M1 Max).

Disclaimer: The resources related to this project are intended for academic research use only.