Update app.py

app.py

@@ -1,4 +1,9 @@
-client = InferenceClient("google/gemma-7b-it")
+from huggingface_hub import InferenceClient
+import gradio as gr
+
+client = InferenceClient(
+    "google/gemma-7b-it"
+)
 
 def format_prompt(message, history):
     prompt = ""
@@ -9,11 +14,15 @@ def format_prompt(message, history):
     prompt += f"<start_of_turn>user{message}<end_of_turn><start_of_turn>model"
     return prompt
 
-def generate(prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
+def generate(
+    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+):
     if not history:
         history = []
+        hist_len=0
     if history:
-        hist_len = len(history)
+        hist_len=len(history)
+        print(hist_len)
 
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -80,7 +89,9 @@ additional_inputs=[
 ]
 
 # Create a Chatbot object with the desired height
-chatbot = gr.Chatbot(height=450, layout="bubble")
+chatbot = gr.Chatbot(height=450,
+                     layout="bubble",
+                     placeholder="Type here to chat...")
 
 with gr.Blocks() as demo:
     gr.HTML("<h1><center>🤖 Google-Gemma-7B-Chat 💬<h1><center>")
@@ -89,6 +100,7 @@ with gr.Blocks() as demo:
         chatbot=chatbot,  # Use the created Chatbot object
         additional_inputs=additional_inputs,
         examples=[["What is the meaning of life?"], ["Tell me something about Mt Fuji."]],
+        placeholder="Type here to chat..."
     )
 
 demo.queue().launch(debug=True)