Update app.py

app.py

@@ -18,21 +18,18 @@ print("Your Computer IP Address is:" + IPAddr)
 DESCRIPTION = """
 # Demo: Breexe-8x7B-Instruct-v0.1
 
-Breexe-8x7B 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.
+Breexe-8x7B is a language model family that builds on top of [Mixtral-8x7B](https://huggingface.co/mistralai/Mistral-7B-v0.1), specifically intended for Traditional Chinese use.
 
 [Breexe-8x7B-Base](https://huggingface.co/MediaTek-Research/Breexe-8x7B-Base-v0.1) is the base model for the Breexe-8x7B series. 
 It is suitable for use if you have substantial fine-tuning data to tune it for your specific use case.
 
 [Breexe-8x7B-Instruct](https://huggingface.co/MediaTek-Research/Breexe-8x7B-Instruct-v0.1) derives from the base model Breexe-8x7B-Base, making the resulting model amenable to be used as-is for commonly seen tasks.
 
-[Breexe-8x7B-Instruct-64k](https://huggingface.co/MediaTek-Research/Breexe-8x7B-Instruct-64k-v0.1) is a slightly modified version of 
-Breexe-8x7B-Instruct to enable a 64k-token context length. Roughly speaking, that is equivalent to 88k Traditional Chinese characters.
-
 The current release version of Breexe-8x7B is v0.1.
 
 *A project by the members (in alphabetical order): Chan-Jan Hsu 許湛然, Chang-Le Liu 劉昶樂, Feng-Ting Liao 廖峰挺, Po-Chun Hsu 許博竣, Yi-Chang Chen 陳宜昌, and the supervisor Da-Shan Shiu 許大山.*
 
-**免責聲明: Breexe-8x7B-Instruct 和 Breexe-8x7B-Instruct-64k 並未針對問答進行安全保護，因此語言模型的任何回應不代表 MediaTek Research 立場。**
+**免責聲明: Breexe-8x7B-Instruct 並未針對問答進行安全保護，因此語言模型的任何回應不代表 MediaTek Research 立場。**
 """
 
 LICENSE = """