Update README.md

README.md

@@ -7,8 +7,6 @@ language:
 
 # Model Card for Breeze-7B-Instruct-v0.1
 
-[Play Demo Here](https://huggingface.co/spaces/MediaTek-Research/Demo_Breeze-7B-Instruct-v0.1)
-
 Breeze-7B is a language model family that builds on top of [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1), specifically intended for Traditional Chinese use.
 
 [Breeze-7B-Base](https://huggingface.co/MediaTek-Research/Breeze-7B-Base-v0.1) is the base model for the Breeze-7B series. 
@@ -62,6 +60,10 @@ Performance-wise:
   - Model type: Causal decoder-only transformer language model
   - Language: English and Traditional Chinese (zh-tw)
 
+## Demo
+
+[Play Demo Here](https://huggingface.co/spaces/MediaTek-Research/Demo_Breeze-7B-Instruct-v0.1)
+
 ## Base Model Performance
 
 **TMMLU+**, **DRCD**, and **Table** source from [MediaTek-Research/TCEval-v2](https://huggingface.co/datasets/MediaTek-Research/TCEval-v2).
@@ -159,10 +161,6 @@ All inferences run on 2 RTX A6000 GPUs (using `vllm`, with a tensor-parallel siz
 
 TBD
 
-## Demo
-
-[Play Demo Here](https://huggingface.co/spaces/MediaTek-Research/Demo_Breeze-7B-Instruct-v0.1)
-
 ## Use in Transformers
 
 First install direct dependencies: