Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral
This work addresses language adaptation for Chinese users, but it is incremental as it builds on an existing model with standard techniques.
The paper tackled the problem of adapting the Mixtral-8x7B-v0.1 language model to improve Chinese language abilities while retaining English performance, achieving enhanced Chinese understanding and generation through further pre-training and instruction fine-tuning.
Mixtral, a representative sparse mixture of experts (SMoE) language model, has received significant attention due to its unique model design and superior performance. Based on Mixtral-8x7B-v0.1, in this paper, we propose Chinese-Mixtral and Chinese-Mixtral-Instruct with improved Chinese language abilities by adopting further pre-training and instruction fine-tuning. Experimental results show that our Chinese-Mixtral and Chinese-Mixtral-Instruct successfully improve Chinese understanding and generation performance while retaining the original English abilities. Then, we discuss several key questions when performing language adaptation on large language models, including the necessity of extending the language-specific vocabulary and the choice of the initialization model (foundation model v.s. instruction model), by providing empirical results and analysis. We also present the visualizations of each expert to examine their importance on downstream tasks. Our resources are publicly available through \url{https://github.com/ymcui/Chinese-Mixtral}.