Update app.py

app.py

@@ -59,7 +59,7 @@ print(f"Model {model_name} loaded successfully on {device}")
 
 # Function to run the text generation process
 def run_generation(user_text, top_p, temperature, top_k, max_new_tokens):
-    template = "\n{}\n"
+    template = "<|context|><|user|>\n{}<|end|>\n<|assistant|>"
     model_inputs = tokenizer(template.format(user_text) if usingAdapter else user_text, return_tensors="pt")
     model_inputs = model_inputs.to(device)
 
@@ -87,7 +87,7 @@ def run_generation(user_text, top_p, temperature, top_k, max_new_tokens):
 
 # Gradio UI setup
 with gr.Blocks(css="""
-    `div.svelte-sfqy0y {
+    div.svelte-sfqy0y {
         display: flex;
         flex-direction: inherit;
         flex-wrap: wrap;
@@ -95,6 +95,7 @@ with gr.Blocks(css="""
         box-shadow: var(--block-shadow);
         border: var(--block-border-width) solid var(--border-color-primary);
         border-radius: var(--block-radius);
+        background: var(--block-background-fill);
         overflow-y: hidden;
         padding: 20px;
     }
@@ -112,8 +113,10 @@ with gr.Blocks(css="""
         padding: 20px;
         border-radius: 8px;
         box-shadow: 0 0 10px rgba(0,0,0,0.5);
+        background: var(--body-background-fill);
     }
     .gr-button {
+        background-color: var(--block-background-fill);
         color: white;
         border: none;
         border-radius: 4px;
@@ -128,6 +131,7 @@ with gr.Blocks(css="""
         width: 100%;
         height: 8px;
         border-radius: 5px;
+        background: #333;
         outline: none;
         opacity: 0.9;
         -webkit-transition: .2s;
@@ -137,6 +141,7 @@ with gr.Blocks(css="""
         opacity: 1;
     }
     .gr-textbox {
+        background-color: var(--block-background-fill);
         color: white;
         border: none;
         border-radius: 4px;
@@ -168,7 +173,7 @@ with gr.Blocks(css="""
             temperature = gr.Slider(minimum=0.1, maximum=5.0, value=0.8, step=0.1, label="Temperature")
         
         with gr.Column(scale=7):
-            model_output = gr.Chatbot(label="Chatbot Output", height=400)
+            model_output = gr.Chatbot(label="Chatbot Output", height=566)
 
     def handle_submit(text, top_p, temperature, top_k, max_new_tokens):
         response = run_generation(text, top_p, temperature, top_k, max_new_tokens)