Update app.py

app.py

@@ -201,7 +201,7 @@ with gr.Blocks(css=STYLE) as hf_endpoint:
                 with gr.Column():
                     gr.Markdown("""## Target model
 
-Import a model from the Hugging Face hub""")
+Model from the Hugging Face hub""")
                     repository_selector = gr.Textbox(
                         value="NousResearch/Nous-Hermes-Llama2-70b",
                         interactive=False,
@@ -212,7 +212,7 @@ Import a model from the Hugging Face hub""")
                 with gr.Column():
                     gr.Markdown("""## Target model version(branch)
 
-Specify the branch name""")
+Branch name of the Model""")
                     revision_selector = gr.Textbox(
                         value=f"main",
                         interactive=False,
@@ -224,14 +224,12 @@ Specify the branch name""")
             with gr.Column():
                 gr.Markdown("""## Endpoint name
 
-Input a name for your new endpoint""")
+Name for your new endpoint""")
                 endpoint_name_input = gr.Textbox(show_label=False, elem_classes=["no-label", "small-big"])
 
             with gr.Row():
                 with gr.Column():
-                    gr.Markdown("""## Cloud Provider
-
-Choose between Amazon Web Services and Microsoft Azure""")
+                    gr.Markdown("""## Cloud Provider""")
                     provider_selector = gr.Dropdown(
                         choices=providers.keys(),
                         interactive=True,
@@ -240,9 +238,7 @@ Choose between Amazon Web Services and Microsoft Azure""")
                     )
 
                 with gr.Column():
-                    gr.Markdown("""## Cloud Region
-
-Choose one of the regions from each cloud provider""")
+                    gr.Markdown("""## Cloud Region""")
                     region_selector = gr.Dropdown(
                         [],
                         value="",
@@ -271,9 +267,7 @@ Choose one of the regions from each cloud provider""")
                     )
 
             with gr.Column():
-                gr.Markdown("""## Select Compute Instance Type
-
-Select a CPU or GPU accelerated compute option for inference""")
+                gr.Markdown("""## Select Compute Instance Type""")
                 compute_selector = gr.Dropdown(
                     [],
                     value="",
@@ -285,9 +279,7 @@ Select a CPU or GPU accelerated compute option for inference""")
             with gr.Row():
                 with gr.Row():
                     with gr.Column():
-                        gr.Markdown("""## Min Number of Nodes
-    
-    Automatically scale the number of replicas based on load and compute usage""")
+                        gr.Markdown("""## Min Number of Nodes""")
                         min_node_selector = gr.Number(
                             value=1,
                             interactive=True,
@@ -296,9 +288,7 @@ Select a CPU or GPU accelerated compute option for inference""")
                         )
     
                     with gr.Column():
-                        gr.Markdown("""## Max Number of Nodes
-    
-    Automatically scale the number of replicas based on load and compute usage""")
+                        gr.Markdown("""## Max Number of Nodes""")
                         max_node_selector = gr.Number(
                             value=1,
                             interactive=True,
@@ -307,9 +297,7 @@ Select a CPU or GPU accelerated compute option for inference""")
                         )
 
                 with gr.Column():
-                    gr.Markdown("""## Security Level
-
-Choose your endpoint's level of privacy""")
+                    gr.Markdown("""## Security Level""")
                     security_selector = gr.Radio(
                         choices=["Protected", "Public", "Private"],
                         value="Public",