Update app.py

app.py

@@ -1,9 +1,8 @@
 from huggingface_hub import InferenceClient
 import gradio as gr
 
-client = InferenceClient(
-    "google/gemma-7b-it"
-)
+# Initialize the InferenceClient
+client = InferenceClient("google/gemma-7b-it")
 
 def format_prompt(message, history):
     prompt = ""
@@ -14,93 +13,57 @@ 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_response(prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
+    # Check if history is empty
     if not history:
         history = []
-        hist_len=0
-    if history:
-        hist_len=len(history)
-        print(hist_len)
-
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
+    # Ensure temperature is within a valid range
+    temperature = max(1e-2, float(temperature))
     top_p = float(top_p)
 
     generate_kwargs = dict(
         temperature=temperature,
-        max_new_tokens=max_new_tokens,
+        max_new_tokens=int(max_new_tokens),
         top_p=top_p,
-        repetition_penalty=repetition_penalty,
+        repetition_penalty=float(repetition_penalty),
         do_sample=True,
         seed=42,
     )
 
     formatted_prompt = format_prompt(prompt, history)
 
+    # Use the InferenceClient for text generation
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    
+    # Concatenate the generated responses
     output = ""
-
     for response in stream:
         output += response.token.text
         yield output
     return output
 
-
-additional_inputs=[
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Max new tokens",
-        value=512,
-        minimum=0,
-        maximum=1048,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=0.90,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1.2,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
-    )
+# Additional input sliders for responsiveness
+additional_inputs = [
+    gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"),
+    gr.Slider(label="Max new tokens", value=512, minimum=0, maximum=1048, step=64, interactive=True, info="The maximum numbers of new tokens"),
+    gr.Slider(label="Top-p (nucleus sampling)", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens"),
+    gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens")
 ]
 
 # Create a Chatbot object with the desired height
-chatbot = gr.Chatbot(height=450,
-                     layout="bubble",
-                     placeholder="Type here to chat...")
+chatbot = gr.Chatbot(height=450, layout="bubble")
 
 with gr.Blocks() as demo:
+    # Display a title
     gr.HTML("<h1><center>🤖 Google-Gemma-7B-Chat 💬<h1><center>")
+    
+    # Use ChatInterface for user interaction
     gr.ChatInterface(
-        generate,
-        chatbot=chatbot,  # Use the created Chatbot object
+        generate_response,
+        chatbot=chatbot,
         additional_inputs=additional_inputs,
         examples=[["What is the meaning of life?"], ["Tell me something about Mt Fuji."]],
-        placeholder="Type here to chat..."
     )
 
+# Launch the Gradio interface
 demo.queue().launch(debug=True)