Update README.md

README.md

@@ -4,6 +4,11 @@ base_model:
 - Qwen/Qwen2.5-7B
 tags:
 - medical
+datasets:
+- zhengyun21/PMC-Patients
+- THUMedInfo/RareArena
+- bigbio/meddialog
+- chenxz/RareBench
 ---
 For implementation detailes, please refer to [DiagRL github repository](https://github.com/MAGIC-AI4Med/DiagRL)
 
@@ -79,6 +84,4 @@ We calculate top-1 and top-5 accuracy among common and rare disease diagnosis da
 | Qwen14B (Env)      | 13.22         | 15.91         | 24.38             | 35.57             | 24.69           | 36.22           | 16.54         | 24.33         | 10.08           | 15.47           | 34.70           | 59.20           |
 | GPT-4o (Env)       | 15.07         | 21.25         | 28.64             | 38.38             | 25.86           | 39.41           | 20.47         | 29.05         | 11.24           | 19.32           | 40.11           | 63.28           |
 | **Ours (Llama8B)** | 21.05         | 27.83         | 34.15             | 45.74             | 35.51           | 46.92           | 42.00         | 55.02         | 22.41           | 29.95           | 64.33           | 73.86           |
-| **Ours (Qwen7B)**  | **33.09**         | **42.87**         | **41.41**         | **46.80**             | **49.28**       | **55.34**           | **52.44**     | **61.53**         | 25.97           | 35.32           | 64.47           | 79.51           |
-
-
+| **Ours (Qwen7B)**  | **33.09**         | **42.87**         | **41.41**         | **46.80**             | **49.28**       | **55.34**           | **52.44**     | **61.53**         | 25.97           | 35.32           | 64.47           | 79.51           |