Update app.py

app.py

@@ -28,11 +28,11 @@ DESCRIPTION = """
 </p>
 
 
-Taiwan-LLaMa is a fine-tuned model specifically designed for traditional Chinese applications. It is built upon the LLaMa 2 architecture and includes a pretraining phase with over 5 billion tokens and fine-tuning with over 490k multi-turn conversational data in Traditional Chinese.
+Taiwan-LLaMa is a fine-tuned model specifically designed for traditional mandarin applications. It is built upon the LLaMa 2 architecture and includes a pretraining phase with over 5 billion tokens and fine-tuning with over 490k multi-turn conversational data in Traditional Mandarin.
 
 ## Key Features
 
-1. **Traditional Chinese Support**: The model is fine-tuned to understand and generate text in Traditional Chinese, making it suitable for Taiwanese culture and related applications.
+1. **Traditional Mandarin Support**: The model is fine-tuned to understand and generate text in Traditional Mandarin, making it suitable for Taiwanese culture and related applications.
 
 2. **Instruction-Tuned**: Further fine-tuned on conversational data to offer context-aware and instruction-following responses.
 
@@ -46,11 +46,11 @@ Different versions of Taiwan-LLaMa are available:
 
 - **Taiwan-LLaMa v1.0 (This demo)**: Optimized for Taiwanese Culture
 - **Taiwan-LLaMa v0.9**: Partial instruction set
-- **Taiwan-LLaMa v0.0**: No Traditional Chinese pretraining
+- **Taiwan-LLaMa v0.0**: No Traditional Mandarin pretraining
 
 The models can be accessed from the provided links in the Hugging Face repository.
 
-Try out the demo to interact with Taiwan-LLaMa and experience its capabilities in handling Traditional Chinese!
+Try out the demo to interact with Taiwan-LLaMa and experience its capabilities in handling Traditional Mandarin!
 """
 
 LICENSE = """