30 lines
1.1 KiB
Markdown
30 lines
1.1 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- medical
|
||
|
|
license: apache-2.0
|
||
|
|
datasets:
|
||
|
|
- OrionLLM/OpenMedicalInstruct
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen2.5-1.5B-Instruct
|
||
|
|
---
|
||
|
|
|
||
|
|
> [!WARNING]
|
||
|
|
> **Experimental model.** This model is intended for research and testing only and **must not be used for real medical diagnosis, treatment, or clinical decision-making**.
|
||
|
|
|
||
|
|
**medqwen** is a small experimental medical reasoning model based on **Qwen2.5-1.5B**.
|
||
|
|
It was trained on **[DedeProGames/Medical-Reasoning-SFT-Nano](https://huggingface.co/datasets/DedeProGames/Medical-Reasoning-SFT-Nano)**.
|
||
|
|
|
||
|
|
medqwen is designed to explore medical-style reasoning, question answering, and instruction following in a compact model size. It is focused on being lightweight, simple, and useful for experimentation.
|
||
|
|
|
||
|
|
## Details
|
||
|
|
|
||
|
|
- **Model name:** medqwen
|
||
|
|
- **Base model:** Qwen2.5-1.5B
|
||
|
|
- **Training dataset:** DedeProGames/Medical-Reasoning-SFT-Nano
|
||
|
|
- **Type:** Experimental medical reasoning model
|
||
|
|
|
||
|
|
## Notes
|
||
|
|
|
||
|
|
This model may generate inaccurate, incomplete, or unsafe medical information.
|
||
|
|
Always verify outputs with trusted medical sources and qualified professionals.
|