added the output [] into llm for llama condition

app.py

@@ -155,8 +155,10 @@ def bot_comms(input_text: str,
 
     if llm_mode == "switch to llama":
         streamer = llama_generation(input_text=input_text, history=history, temperature=temperature, max_new_tokens=max_new_tokens)
+        outputs = []
         for text in streamer:
-            yield text
+            outputs.append(text)
+            yield "".join(outputs)
 
     if llm_mode == "switch to gpt-4o":
         stream = gpt_generation(input=input_text, llama_output="", mode="gpt-4o")