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
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。