Saved in:
Bibliographic Details
Main Authors: Fan, Chenghao, Lu, Zhenyi, Tian, Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.12737
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913797358223360
author Fan, Chenghao
Lu, Zhenyi
Tian, Jie
author_facet Fan, Chenghao
Lu, Zhenyi
Tian, Jie
contents Chinese-Vicuna is an open-source, resource-efficient language model designed to bridge the gap in Chinese instruction-following capabilities by fine-tuning Meta's LLaMA architecture using Low-Rank Adaptation (LoRA). Targeting low-resource environments, it enables cost-effective deployment on consumer GPUs (e.g., RTX-2080Ti for 7B models) and supports domain-specific adaptation in fields like healthcare and law. By integrating hybrid datasets (BELLE and Guanaco) and 4-bit quantization (QLoRA), the model achieves competitive performance in tasks such as translation, code generation, and domain-specific Q\&A. The project provides a comprehensive toolkit for model conversion, CPU inference, and multi-turn dialogue interfaces, emphasizing accessibility for researchers and developers. Evaluations indicate competitive performance across medical tasks, multi-turn dialogue coherence, and real-time legal updates. Chinese-Vicuna's modular design, open-source ecosystem, and community-driven enhancements position it as a versatile foundation for Chinese LLM applications.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12737
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Chinese-Vicuna: A Chinese Instruction-following Llama-based Model
Fan, Chenghao
Lu, Zhenyi
Tian, Jie
Computation and Language
Chinese-Vicuna is an open-source, resource-efficient language model designed to bridge the gap in Chinese instruction-following capabilities by fine-tuning Meta's LLaMA architecture using Low-Rank Adaptation (LoRA). Targeting low-resource environments, it enables cost-effective deployment on consumer GPUs (e.g., RTX-2080Ti for 7B models) and supports domain-specific adaptation in fields like healthcare and law. By integrating hybrid datasets (BELLE and Guanaco) and 4-bit quantization (QLoRA), the model achieves competitive performance in tasks such as translation, code generation, and domain-specific Q\&A. The project provides a comprehensive toolkit for model conversion, CPU inference, and multi-turn dialogue interfaces, emphasizing accessibility for researchers and developers. Evaluations indicate competitive performance across medical tasks, multi-turn dialogue coherence, and real-time legal updates. Chinese-Vicuna's modular design, open-source ecosystem, and community-driven enhancements position it as a versatile foundation for Chinese LLM applications.
title Chinese-Vicuna: A Chinese Instruction-following Llama-based Model
topic Computation and Language
url https://arxiv.org/abs/2504.12737