Update app.py

app.py

@@ -1,30 +1,40 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Load model directly
+# Load model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained("Leo022/Gemma_QA_For_Telegram_Bot")
 model = AutoModelForCausalLM.from_pretrained("Leo022/Gemma_QA_For_Telegram_Bot")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
+    """
+    Function to generate response from the model.
+    Args:
+        message (str): The user's input message.
+        history (list): The conversation history.
+        system_message (str): The system message.
+        max_tokens (int): Maximum number of tokens for output.
+        temperature (float): Sampling temperature.
+        top_p (float): Nucleus sampling parameter.
+    Returns:
+        str: The model's response.
+    """
+    # Initialize messages list with the system message
     messages = [{"role": "system", "content": system_message}]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Add conversation history to messages
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
 
+    # Append the latest user message
     messages.append({"role": "user", "content": message})
 
-    input_ids = tokenizer.encode(" ".join([m["content"] for m in messages]), return_tensors="pt")
+    # Encode the concatenation of all message contents
+    input_ids = tokenizer.encode(" ".join([msg["content"] for msg in messages]), return_tensors="pt")
 
+    # Generate response
     output = model.generate(
         input_ids,
         max_length=max_tokens,
@@ -33,25 +43,22 @@ def respond(
         do_sample=True,
     )
 
+    # Decode the generated tokens to get the response text
     response = tokenizer.decode(output[0], skip_special_tokens=True)
 
     return response
 
+# Define the Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
 if __name__ == "__main__":
+    # Launch the Gradio app
     demo.launch()