Update app.py

app.py

@@ -5,14 +5,16 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 DESCRIPTION = """\
-# EvaByte SFT
+# EvaByte [Byte-Level LLM]
 
-EvaByte is a byte-level language model that combines multibyte prediction with the efficient EVA attention mechanism.  
-This page hosts [EvaByte/EvaByte-SFT](https://huggingface.co/EvaByte/EvaByte-SFT), fine-tuned via supervised instruction data to enable chat and general instruction-following capabilities.  
+EvaByte is a efficient　byte-level language model with multibyte prediction and EVA attention, built by the University of Hong Kong and SambaNova Systems.  
+This Space is an unofficial demo of the instruction-tuned version [EvaByte/EvaByte-SFT](https://huggingface.co/EvaByte/EvaByte-SFT).
 For full details on architecture, training recipe, and benchmarks, see their blog post and the project repository:
 
 - Blog: <https://hkunlp.github.io/blog/2025/evabyte>  
 - GitHub: <https://github.com/OpenEvaByte/evabyte>
+
+If you liked this Space, follow me on Twitter: [@KantaHayashiAI](https://x.com/KantaHayashiAI)
 """
 
 MAX_MAX_NEW_TOKENS = 2048