Jpharmatron 7B

🚀 JPharmatron-7B

JPharmatron-7B是一款专为制药应用和研究设计的70亿参数大语言模型，能在制药文书和研究领域发挥重要作用。

✨ 主要特性

• 基于Qwen2.5 - 7B持续预训练，使用来自日语和英语数据集的88亿个标记，相比JPharmatron - 7B - base模型，通过Qwen2.5 - 7B - Instruct的聊天向量增强了聊天能力。
• 专为制药文书和研究应用而设计，不适用于医疗用途或其他对风险敏感的用途。
• 在与同规模的其他通用/特定领域模型的评估对比中，在五个基准测试中均取得了最高分。

📚 详细文档

模型详情

模型描述

JPharmatron - 7B基于Qwen2.5 - 7B，使用来自日语和英语数据集的88亿个标记进行持续预训练。与JPharmatron - 7B - base模型相比，它从Qwen2.5 - 7B - Instruct的聊天向量中获得了增强的聊天能力。

• 开发者：EQUES Inc.
• 资助方：GENIAC项目
• 模型类型：自回归解码器
• 支持语言：日语、英语
• 许可证：CC - BY - SA - 4.0

模型资源

• 仓库地址：https://github.com/EQUES-Inc/pharma-LLM-eval
• 论文：A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP

应用场景

此模型旨在用于制药文书和研究应用，未经过医疗用途或其他对风险敏感用途的验证。

评估

我们将JPharmatron - 7B模型与其他同规模的通用/特定领域模型进行了评估对比。

测试数据

使用了JPharmaBench和两个现有基准测试（JMMLU (pharma) 和IgakuQA）。

评估结果

与Meditron3 - Qwen2.5 - 7B和Llama3.1 - Swallow - 8B - Instruct - v0.3相比，JPharmatron - 7B在所有五个基准测试中均取得了最高分。

引用信息

BibTeX：

@misc{sukeda_japanese_2025,
  title     = {A {Japanese} {Language} {Model} and {Three} {New} {Evaluation} {Benchmarks} for {Pharmaceutical} {NLP}},
  url       = {http://arxiv.org/abs/2505.16661},
  doi       = {10.48550/arXiv.2505.16661},
  abstract  = {We present a Japanese domain-specific language model for the pharmaceutical field, developed through continual pretraining on 2 billion Japanese pharmaceutical tokens and 8 billion English biomedical tokens. To enable rigorous evaluation, we introduce three new benchmarks: YakugakuQA, based on national pharmacist licensing exams; NayoseQA, which tests cross-lingual synonym and terminology normalization; and SogoCheck, a novel task designed to assess consistency reasoning between paired statements. We evaluate our model against both open-source medical LLMs and commercial models, including GPT-4o. Results show that our domain-specific model outperforms existing open models and achieves competitive performance with commercial ones, particularly on terminology-heavy and knowledge-based tasks. Interestingly, even GPT-4o performs poorly on SogoCheck, suggesting that cross-sentence consistency reasoning remains an open challenge. Our benchmark suite offers a broader diagnostic lens for pharmaceutical NLP, covering factual recall, lexical variation, and logical consistency. This work demonstrates the feasibility of building practical, secure, and cost-effective language models for Japanese domain-specific applications, and provides reusable evaluation resources for future research in pharmaceutical and healthcare NLP. Our model, codes, and datasets are released at https://github.com/EQUES-Inc/pharma-LLM-eval.},
  urldate   = {2025-05-30},
  publisher = {arXiv},
  author    = {Sukeda, Issey and Fujii, Takuro and Buma, Kosei and Sasaki, Shunsuke and Ono, Shinnosuke},
  month     = may,
  year      = {2025},
  note      = {arXiv:2505.16661 [cs]},
  annote    = {Comment: 15 pages, 9 tables, 5 figures}
}

更多信息

请参阅我们的预印本：A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP。

模型卡片作者

@shinnosukeono