Update app.py

app.py

@@ -27,7 +27,7 @@ if torch.cuda.is_available():
     model_id = "FuseAI/FuseChat-7B-VaRM"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
-    tokenizer.use_default_system_prompt = False
+    tokenizer.use_default_system_prompt = True
 
 
 @spaces.GPU(enable_queue=True)
@@ -54,7 +54,7 @@ def generate(
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=False)
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,