Update app.py

app.py

@@ -9,7 +9,7 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-DESCRIPTION = "# RakutenAI-7B-chat"
+DESCRIPTION = "# Sakaltum-7B-chat"
 
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
@@ -19,7 +19,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "32768"))
 
 if torch.cuda.is_available():
-    model_id = "Rakuten/RakutenAI-7B-chat"
+    model_id = "sakaltcommunity/sakaltum-7b"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
     model.eval()
     tokenizer = AutoTokenizer.from_pretrained(model_id)
@@ -130,4 +130,4 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()