Update app.py

app.py

@@ -7,12 +7,12 @@ client = InferenceClient(
 
 
 def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
 
 def generate(
     prompt, history, temperature=0.9, max_new_tokens=16000, top_p=0.95, repetition_penalty=1.0,):
@@ -24,7 +24,6 @@ def generate(
         do_sample=True,
         seed=42,)
     formatted_prompt = format_prompt(prompt, history)
-
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
 
@@ -34,7 +33,7 @@ def generate(
     return output
 
 css = """
-  #mkd {
+    #mkd {
     height: 500px; 
     overflow: auto; 
     border: 1px solid #ccc;