Update app.py

app.py

@@ -18,7 +18,7 @@ def generate(
     pipe = load_model(model_name)
 
     # Set tokenize correctly. Otherwise ticking the box breaks it.
-    prompt = f"<|im_start|>user\n{user_input}<|im_end|>\n"
+    prompt = f"<|im_start|>user\n{user_input}<|im_end|>\n<|im_start|>assistant\n"
     outputs = pipe(prompt, max_new_tokens=max_new_tokens, do_sample=True,
                    temperature=temperature, top_k=top_k, top_p=top_p, repetition_penalty=1.10)
     return outputs[0]["generated_text"]