README.md

---
license: afl-3.0
language:
- en
- zh
metrics:
- accuracy
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
pipeline_tag: text-generation
library_name: transformers
tags:
- medical
- deepseek-r1
- health
- ehr
- reasoning
# 核心配置：开启门控
gated: true

# （可选）申请表单上方的提示语
extra_gated_heading: "Access Request"
extra_gated_description: "Please provide your organization and intended use."

# （核心）自定义问卷字段
extra_gated_fields:
  Affiliation: text          # 单位/机构（文本框，满足你的需求）
  Research Purpose: text     # 研究用途（文本框）
  Country: text              # 国家（文本框）
---

# RareSeek-R1: A specialized language model for rare disease diagnosis and reasoning

**RareSeek-R1** is a domain-specialized large language model for rare-disease diagnostic reasoning, developed through a Progressive Parameter-Efficient Transfer Learning framework. The model is first instruction-tuned on the clinically grounded RareMed-Corpus, a large, multi-source dataset deeply integrated from medical textbooks, guidelines, biomedical literature, and real-world EHR narratives. It is then fine-tuned on RareMed-CoT, a high-fidelity corpus designed to instill explicit, stepwise clinical reasoning aligned with real diagnostic workflows. To further enhance factual reliability, GraphRAG is incorporated to anchor the model’s inference to up-to-date variant–gene–phenotype–disease relationships. This retrieval augmentation substantially reduces hallucinations, improves factual calibration, and yields notable performance gains—particularly when EHR narratives are combined with prioritized genetic variants. Together, RareSeek-R1 performs direct reasoning over full-length EHRs, leverages graph-grounded retrieval, and demonstrably augments clinician-level diagnostic accuracy, advancing a reliable and scalable AI paradigm for rare-disease diagnosis.

<p align="center">
  <img src="https://github.com/yangtao1025/RareSeek-R1/raw/main/RareSeek-R1.png" alt="RareSeek-R1 Teaser Image" width="800">
</p>

# **RareMedData**: [https://huggingface.co/datasets/TaoMedAI/RareMedData](https://huggingface.co/datasets/TaoMedAI/RareMedData)