Update README.md

README.md

@@ -1,12 +1,25 @@
----
-title: Qwen3 Medical
-emoji: 📊
-colorFrom: gray
-colorTo: pink
-sdk: docker
-pinned: false
-license: mit
-short_description: using lastmass/Qwen3_Medical_GRPO demo
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Qwen3 Medical
+emoji: 📊
+colorFrom: gray
+colorTo: pink
+sdk: docker
+pinned: false
+license: mit
+short_description: lastmass/Qwen3_Medical_GRPO Demo
+models:
+- lastmass/Qwen3_Medical_GRPO
+datasets:
+- lastmass/Qwen3_Medical_GRPO
+---
+
+This Space demonstrates the **lastmass/Qwen3_Medical_GRPO** model (Q4_K_M quantized version).
+
+⚠️ **Please Note:** This demo runs on Hugging Face's provided free CPU hardware, so inference is **very slow**.
+
+For a much better and faster experience, we highly recommend running inference **locally** on your own machine with a GPU. 
+Please refer to the source model repository **[lastmass/Qwen3_Medical_GRPO](https://huggingface.co/lastmass/Qwen3_Medical_GRPO)** 
+for detailed usage instructions. For optimal performance, it is suggested to use **vLLM** for inference.
+
+
+---