---
language:
- en
base_model:
- Qwen/Qwen2.5-3B-Instruct
- Qwen/Qwen2.5-7B-Instruct
datasets:
- KevinZonda/PubMed-IV
pipeline_tag: text-generation
tags:
- medical
- biology
---

# MedSPO Family

MedSPO is a model family which fine-tuned Qwen2.5-Instruct model specifically designed for biomedical subject-predicate-object (SPO) extraction tasks. This model is trained on the PubMed-IV dataset using SPO extraction knowledge distilled from [DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324).

| Model     | Parameters | Base Model          | Huggingface |
| :-------: | :--------: | :-----------------: | ----------- |
| MedSPO-7B | 7B         | Qwen2.5-7B-Instruct | [KevinZonda/MedSPO-7B](https://huggingface.co/KevinZonda/MedSPO-7B) |
| MedSPO-3B | 3B         | Qwen2.5-3B-Instruct | [KevinZonda/MedSPO-3B](https://huggingface.co/KevinZonda/MedSPO-3B) |

## Magic Prompt

System Prompt:
```plain
You are a biomedical specialist. You are given one paper (title, abstract, conclusion). Extract all biomedical-related Subject-Predicate-Object (SPO) Triple in valid JSON format wrapped in <output> tag.
```
User Prompt:
```xml
<input>
    <title></title>
    <abstract></abstract>
    <conclusion></conclusion>
</input>
```