Update app.py

app.py

@@ -37,8 +37,8 @@ def generate(prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition
 
     for response in stream:
         output += response.token.text
-        yield output
-    return output
+        yield output.strip('</s>')
+    return output.strip('</s>')
 
 with gr.Blocks() as demo:
     input_text = gr.Textbox(placeholder="Enter your prompt here...", lines=2, max_lines=2, label="Prompt")