Update app.py

app.py

@@ -7,6 +7,7 @@ import gradio as gr
 from gradio import FileData
 import time
 import spaces
+import re
 ckpt = "Xkev/Llama-3.2V-11B-cot"
 model = MllamaForConditionalGeneration.from_pretrained(ckpt,
     torch_dtype=torch.bfloat16).to("cuda")
@@ -68,7 +69,8 @@ def bot_streaming(message, history, max_new_tokens=250):
         buffer += new_text
         generated_text_without_prompt = buffer
         time.sleep(0.01)
-        buffer.replace("<", "").replace(">", "")
+        buffer = re.sub(r"<.*?>", "", buffer)
+        print(f"Buffer: {buffer}")
         yield buffer