arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.12480cs.LGcs.CL
收藏

Vintern-1B:一种面向越南语的高效多模态大语言模型

Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese

Khang T. Doan, Bao G. Huynh, Dung T. Hoang, Thuc D. Pham, Nhat H. Pham, Quan T. M. Nguyen, Bang Q. Vo, Suong N. Hoang

AI总结:

本文提出 Vintern-1B,一种面向越南语任务的 10 亿参数多模态大语言模型,结合 Qwen2-0.5B 与 InternViT 视觉模型,在超 300 万图文对上微调,在多个越南语基准上表现稳健,且支持端侧部署。

摘要:

在本报告中,我们介绍了 Vintern-1B,这是一种用于越南语任务的可靠 10 亿参数多模态大语言模型(MLLM)。通过将 Qwen2-0.5B-Instruct 语言模型与 InternViT-300M-448px 视觉模型相结合,Vintern-1B 针对一系列应用进行了优化,包括越南语语境中的光学字符识别(OCR)、文档提取和通用问答。该模型在包含超过 300 万个图像-问答对的庞大数据集上进行了微调,在 OpenViVQA 和 ViTextVQA 等多个越南语基准上取得了稳健的性能和可靠的结果。Vintern-1B 足够小,可以轻松适应各种端侧应用。此外,我们还开源了多个用于文本和图表的越南语视觉问答(VQA)数据集,这些数据集是使用 Gemini 1.5 Flash 创建的。我们的模型可在以下地址获取:https://huggingface.co/5CD-AI/Vintern-1B-v2。

英文摘要:

In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model, Vintern-1B is optimized for a range of applications, including optical character recognition (OCR), document extraction, and general question-answering in Vietnamese context. The model is fine-tuned on an extensive dataset of over 3 million image-question-answer pairs, achieving robust performance and reliable results across multiple Vietnamese language benchmarks like OpenViVQA and ViTextVQA. Vintern-1B is small enough to fit into various on-device applications easily. Additionally, we have open-sourced several Vietnamese vision question answering (VQA) datasets for text and diagrams, created with Gemini 1.5 Flash. Our models are available at: https://huggingface.co/5CD-AI/Vintern-1B-v2.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑