Upload 3 files

app.py

@@ -252,10 +252,22 @@ with gr.Blocks(title="Context Window Extender - Chat") as demo:
     )
     
     with gr.Row():
-        max_new_tokens = gr.Slider(minimum=10, maximum=4096, value=256, step=10, label="Max New Tokens")
+        max_new_tokens = gr.Slider(minimum=10, maximum=32768, value=256, step=10, label="Max New Tokens")
         temperature = gr.Slider(minimum=0.0, maximum=2.0, value=0.7, step=0.1, label="Temperature")
         top_p = gr.Slider(minimum=0.0, maximum=1.0, value=0.9, step=0.05, label="Top-p")
     
+    # Update max_new_tokens slider max based on context multiplier
+    def update_max_tokens(multiplier):
+        base = 32768
+        max_tokens = calculate_context_length(base, multiplier)
+        return gr.update(maximum=max_tokens)
+    
+    context_multiplier.change(
+        fn=update_max_tokens,
+        inputs=[context_multiplier],
+        outputs=[max_new_tokens]
+    )
+    
     # Hide/show RoPE options based on extension method
     def update_rope_visibility(method):
         return gr.update(visible=method == "rope"), gr.update(visible=method == "rope")