Add application file

app.py

@@ -125,13 +125,13 @@ g = gr.Interface(
     fn=evaluate,
     inputs=[
         gr.components.Textbox(
-            lines=2, label="Instruction", placeholder="Tell me about alpacas."
+            lines=2, label="Instruction", placeholder="Generate an attractive advertisement for this product."
         ),
         gr.components.Textbox(lines=2, label="Input", placeholder="none"),
         gr.components.Slider(minimum=0, maximum=1, value=0.1, label="Temperature"),
         gr.components.Slider(minimum=0, maximum=1, value=0.75, label="Top p"),
         gr.components.Slider(minimum=0, maximum=100, step=1, value=40, label="Top k"),
-        gr.components.Slider(minimum=1, maximum=4, step=1, value=4, label="Beams"),
+        gr.components.Slider(minimum=1, maximum=4, step=1, value=1, label="Beams"),
         gr.components.Slider(
             minimum=1, maximum=512, step=1, value=128, label="Max tokens"
         ),
@@ -143,7 +143,7 @@ g = gr.Interface(
         )
     ],
     title="🦙🛍️ LLaMA-E",
-    description="LLaMA-E is a series of fine-tuned LLaMA model following the E-commerce instructions. It is developed by DSMI (http://dsmi.tech/) @ University of Technology Sydney, and trained on the 120k instruction set. This model is for academic research use only. For more details please contact: Kaize.Shi@uts.edu.au",
+    description="LLaMA-E is meticulously crafted for e-commerce authoring tasks, incorporating specialized features to excel in generating product descriptions, advertisements, and other related content, as outlined in https://arxiv.org/abs/2308.04913#/. The model can be found at https://huggingface.co/DSMI/LLaMA-E#/. The demo here runs on the CPU. We strongly recommend running the model locally with GPU.",
 )
 g.queue(concurrency_count=1)
 g.launch()