Chinese-LLaMA-Alpaca

This project has open-sourced the Chinese LLaMA model and the Alpaca large model fine-tuned with Chinese instructions to further promote open research on large models in the Chinese NLP community. These models expand the Chinese vocabulary based on the original LLaMA and undergo secondary pre-training using Chinese data, enhancing their Chinese language understanding capabilities. Additionally, the Chinese Alpaca model undergoes further fine-tuning using Chinese instruction data, significantly improving the model’s comprehension and execution of instructions.

Technical Report (V2): [Cui, Yang, and Yao] Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca

Main contents of this project:

🚀 Expanded Chinese vocabulary for the original LLaMA model, improving Chinese encoding and decoding efficiency
🚀 Open-sourced the Chinese LLaMA model pre-trained with Chinese text data and the Chinese Alpaca model fine-tuned with instructions
🚀 Open-sourced pre-training scripts and fine-tuning scripts, allowing users to further train the models as needed
🚀 Quick deployment and local quantization experience for large models on personal computers (CPU/GPU)
🚀 Support for 🤗transformers, llama.cpp, text-generation-webui, LlamaChat, LangChain, privateGPT, and other ecosystems

Currently open-sourced model versions: 7B (Base, Plus, Pro), 13B (Base, Plus, Pro), 33B (Base, Plus, Pro)