Update app.py

app.py

@@ -111,8 +111,8 @@ def respond(
 PLACEHOLDER = """
 <div class="message-bubble-border" style="display:flex; max-width: 600px; border-radius: 8px; box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); backdrop-filter: blur(10px);">
     <div style="padding: .5rem 1.5rem;">
-        <h2 style="text-align: left; font-size: 1.5rem; font-weight: 700; margin-bottom: 0.5rem;">Chat with CausalLM 34B (8-bit GGUF)</h2>
-        <p style="text-align: left; font-size: 16px; line-height: 1.5; margin-bottom: 15px;">You can try different models from CausalLM here.<br>Running on NVIDIA A100-SXM4-80GB MIG 3g.40gb with Zero-GPU from Hugging Face.</p>
+        <h2 style="text-align: left; font-size: 1.5rem; font-weight: 700; margin-bottom: 0.5rem;">Chat with Dorna-Llama3 8B </h2>
+        <p style="text-align: left; font-size: 16px; line-height: 1.5; margin-bottom: 15px;">You can try different models.<br>Running on CPU from Hugging Face.</p>
     </div>
 </div>
 """
@@ -145,10 +145,10 @@ demo = gr.ChatInterface(
             label="Repetition penalty",
         ),
         gr.Dropdown([
-                'myCauslLM-34b-beta-v0.1-q8.gguf',
-                '35b-beta-long-Q6_K.gguf',
+                'dorna-llama3-8b-instruct.Q2_K.gguf',
+                'dorna-llama3-8b-instruct.Q4_0.gguf',
             ],
-            value="myCauslLM-34b-beta-v0.1-q8.gguf",
+            value="dorna-llama3-8b-instruct.Q2_K.gguf",
             label="Model"
         ),
     ],
@@ -168,7 +168,7 @@ demo = gr.ChatInterface(
     undo_btn="Undo",
     clear_btn="Clear",
     submit_btn="Send",
-    description="Chat with CausalLM 34B (8-bit GGUF)",
+    description="Chat with Dorna-Llama3 8B (2-bit GGUF)",
     chatbot=gr.Chatbot(scale=1, placeholder=PLACEHOLDER)
 )