Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Rongsheng, Chen, Haoming, Zhou, Ruizhe, Duan, Yaofei, Cai, Kunyan, Ma, Han, Cui, Jiaxi, Li, Jian, Pang, Patrick Cheong-Iao, Wang, Yapeng, Tan, Tao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913181469769728
author Wang, Rongsheng
Chen, Haoming
Zhou, Ruizhe
Duan, Yaofei
Cai, Kunyan
Ma, Han
Cui, Jiaxi
Li, Jian
Pang, Patrick Cheong-Iao
Wang, Yapeng
Tan, Tao
author_facet Wang, Rongsheng
Chen, Haoming
Zhou, Ruizhe
Duan, Yaofei
Cai, Kunyan
Ma, Han
Cui, Jiaxi
Li, Jian
Pang, Patrick Cheong-Iao
Wang, Yapeng
Tan, Tao
contents Existing research has demonstrated that refining large language models (LLMs) through the utilization of machine-generated instruction-following data empowers these models to exhibit impressive zero-shot capabilities for novel tasks, without requiring human-authored instructions. In this paper, we systematically investigate, preprocess, and integrate three Chinese instruction-following datasets with the aim of enhancing the Chinese conversational capabilities of Mixtral-8x7B sparse Mixture-of-Experts model. Through instruction fine-tuning on this carefully processed dataset, we successfully construct the Mixtral-8x7B sparse Mixture-of-Experts model named "Aurora." To assess the performance of Aurora, we utilize three widely recognized benchmark tests: C-Eval, MMLU, and CMMLU. Empirical studies validate the effectiveness of instruction fine-tuning applied to Mixtral-8x7B sparse Mixture-of-Experts model. This work is pioneering in the execution of instruction fine-tuning on a sparse expert-mixed model, marking a significant breakthrough in enhancing the capabilities of this model architecture. Our code, data and model are publicly available at https://github.com/WangRongsheng/Aurora
format Preprint
id arxiv_https___arxiv_org_abs_2312_14557
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning
Wang, Rongsheng
Chen, Haoming
Zhou, Ruizhe
Duan, Yaofei
Cai, Kunyan
Ma, Han
Cui, Jiaxi
Li, Jian
Pang, Patrick Cheong-Iao
Wang, Yapeng
Tan, Tao
Computation and Language
Existing research has demonstrated that refining large language models (LLMs) through the utilization of machine-generated instruction-following data empowers these models to exhibit impressive zero-shot capabilities for novel tasks, without requiring human-authored instructions. In this paper, we systematically investigate, preprocess, and integrate three Chinese instruction-following datasets with the aim of enhancing the Chinese conversational capabilities of Mixtral-8x7B sparse Mixture-of-Experts model. Through instruction fine-tuning on this carefully processed dataset, we successfully construct the Mixtral-8x7B sparse Mixture-of-Experts model named "Aurora." To assess the performance of Aurora, we utilize three widely recognized benchmark tests: C-Eval, MMLU, and CMMLU. Empirical studies validate the effectiveness of instruction fine-tuning applied to Mixtral-8x7B sparse Mixture-of-Experts model. This work is pioneering in the execution of instruction fine-tuning on a sparse expert-mixed model, marking a significant breakthrough in enhancing the capabilities of this model architecture. Our code, data and model are publicly available at https://github.com/WangRongsheng/Aurora
title Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning
topic Computation and Language
url https://arxiv.org/abs/2312.14557