Update app.py

app.py

@@ -8,9 +8,9 @@ client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 def format_prompt(message, history):
     prompt = "<s>"
     for user_prompt, bot_response in history:
-        prompt += f"\[INST\] {user_prompt} \[/INST\]"
+        prompt += f"[INST] {user_prompt} [/INST]"
         prompt += f" {bot_response}</s> "
-    prompt += f"\[INST\] {message} \[/INST\]"
+    prompt += f"[INST] {message} [/INST]"
     return prompt
 
 def generate(prompt, history, system_prompt, temperature=0.9, max_new_tokens=9048, top_p=0.95, repetition_penalty=1.0):
@@ -24,18 +24,15 @@ def generate(prompt, history, system_prompt, temperature=0.9, max_new_tokens=904
         do_sample=True,
         seed=42,
     )
-
     now = datetime.datetime.now()
     formatted_time = now.strftime("%H:%M:%S, %B %d, %Y")
     system_prompt = f"System time: {formatted_time}"
-
     formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-
     output = ""
     for response in stream:
         output += response.token.text
-    yield output
+        yield output
 
 additional_inputs = [
     gr.Textbox(label="System Prompt", max_lines=1, interactive=True),
@@ -47,7 +44,7 @@ additional_inputs = [
 
 gr.ChatInterface(
     fn=generate,
-    chatbot=gr.Chatbot(show_label=True, show_share_button=False, show_copy_button=True, likeable=True, layout="panel", height="auto", ),
+    chatbot=gr.Chatbot(show_label=True, show_share_button=False, show_copy_button=True, likeable=True, layout="panel", height="auto"),
     additional_inputs=additional_inputs,
     title="ConvoLite",
     submit_btn="➢",