Update app.py

app.py

@@ -7,6 +7,8 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, Qwen2TokenizerFast, TextIteratorStreamer
 
+# based on gemma demo code
+
 DESCRIPTION = """\
 # SeaLLMs Med
 
@@ -20,7 +22,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 #model_id = "SeaLLMs/SeaLLMs-v3-7B-Chat"
-model_id = "SeaLLMs/debug_v2.1"
+model_id = "SeaLLMs/debug_4"
 tokenizer = Qwen2TokenizerFast.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,