Update app.py

app.py

@@ -18,8 +18,8 @@ hf_hub_download(
     local_dir = "./models"
 )
 hf_hub_download(
-    repo_id="nisten/q3-reasoner-gguf",
-    filename="unsloth.Q8_0.gguf",
+    repo_id="bartowski/Mistral-Small-24B-Instruct-2501-GGUF",
+    filename="Mistral-Small-24B-Instruct-2501-Q8_0.gguf",
     local_dir = "./models"
 )
 
@@ -164,7 +164,7 @@ PLACEHOLDER = """
         <div style="display: flex; justify-content: space-between; align-items: center;">
             <div style="display: flex; flex-flow: column; justify-content: space-between;">
                 <span style="display: inline-flex; align-items: center; border-radius: 0.375rem; background-color: rgba(229, 70, 77, 0.1); padding: 0.1rem 0.75rem; font-size: 0.75rem; font-weight: 500; color: #f88181; margin-bottom: 2.5px;">
-                    q3-reasoner-qwen-2.5-3B
+                    Mistral Small 24B Instruct 2501
                 </span>
                 <span style="display: inline-flex; align-items: center; border-radius: 0.375rem; background-color: rgba(79, 70, 229, 0.1); padding: 0.1rem 0.75rem; font-size: 0.75rem; font-weight: 500; color: #60a5fa; margin-top: 2.5px;">
                     Meta Llama 3 70B Instruct
@@ -199,7 +199,7 @@ demo = gr.ChatInterface(
             value="unsloth.Q8_0.gguf",
             label="Model"
         ),
-        gr.Textbox(value="Adopt the persona of stephen hawking.Use <reasoning> </reasoning> tags now to deduce what the user wants via first principles based reasoning, always use at least 6 reasoning steps and do a root cause analysus, and then after write the answer as <answer>. Use lots of markdown formatting and emojis. Be extensive with the responses just like Stephen Hawkings would.Always reason stuff out before answering.", label="System message"),
+        gr.Textbox(value="You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.", label="System message"),
         gr.Slider(minimum=1, maximum=4096, value=2048, step=1, label="Max tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(