Update app.py

app.py

@@ -138,7 +138,8 @@ def chat_llama3_8b(message: str,
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
     
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-
+    print(max_new_tokens)
+    max_new_tokens=4096
     generate_kwargs = dict(
         input_ids= input_ids,
         streamer=streamer,