Update app.py

app.py

@@ -14,8 +14,7 @@ def format_prompt(message, history):
     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,):
+def generate(prompt, history, temperature=0.9, max_new_tokens=16000, top_p=0.95, repetition_penalty=1.0,):
         generate_kwargs = dict(
         temperature=temperature,
         max_new_tokens=max_new_tokens,
@@ -27,10 +26,10 @@ def generate(
         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
-    return output
+        for response in stream:
+            output += response.token.text
+            yield output
+        return output
 
 css = """
     #mkd {