Just a bit more UI improvements

- Rephrase the article link sentence
- Add a brain and buble icon for differente steps

app.py

@@ -94,10 +94,7 @@ def bot(history: list, max_num_tokens: int, final_num_tokens: int):
         gr.ChatMessage(
             role="assistant",
             content=str(""),
-            metadata={
-                "title": "Thinking",
-                "status": "pending",
-            },
+            metadata={"title": "🧠 Thinking...", "status": "pending"},
         )
     )
 
@@ -124,7 +121,7 @@ def bot(history: list, max_num_tokens: int, final_num_tokens: int):
         # rebuild the history with the new content
         history[-1].content += prepend.format(question=question)
         if ANSWER_MARKER in prepend:
-            history[-1].metadata["status"] = "done"
+            history[-1].metadata = {"title": "💭 Thoughs", "status": "done"}
             # stop thinking, this is the answer now (no metadata for intermediate steps)
             history.append(gr.ChatMessage(role="assistant", content=""))
         for token in streamer:
@@ -146,7 +143,7 @@ with gr.Blocks(fill_height=True, title="Making any model reasoning") as demo:
             This interface uses *{model_name}* model which is **not** a reasoning model. The used method
             is only to force some "reasoning" steps with prefixes to help the model to enhance the answer.
 
-            See related article here: [Make any model reasoning](https://huggingface.co/blog/Metal3d/making-any-model-reasoning)
+            See my related article here: [Make any model reasoning](https://huggingface.co/blog/Metal3d/making-any-model-reasoning)
             """)
             chatbot = gr.Chatbot(
                 scale=1,