Update app.py

app.py

@@ -1,64 +1,28 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    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]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
+from transformers import BlenderbotForConditionalGeneration, BlenderbotTokenizer
+
+# Load BlenderBot model and tokenizer
+model_name = "facebook/blenderbot-400M-distill"
+model = BlenderbotForConditionalGeneration.from_pretrained(model_name)
+tokenizer = BlenderbotTokenizer.from_pretrained(model_name)
+
+def respond(message, history):
+    # Format history for BlenderBot (requires previous turns)
+    chat_history = "\n".join([f"User: {h[0]}\nBot: {h[1]}" for h in history])
+    full_text = f"{chat_history}\nUser: {message}\nBot:"
+    
+    # Tokenize and generate
+    inputs = tokenizer([full_text], return_tensors="pt", truncation=True, max_length=512)
+    reply_ids = model.generate(**inputs, max_length=200, temperature=0.9)
+    response = tokenizer.batch_decode(reply_ids, skip_special_tokens=True)[0]
+    
+    # Extract only the latest bot response
+    return response.split("Bot:")[-1].strip()
+
+# Launch with Gradio
+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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+    title="🤖 Friendly BlenderBot",
+    examples=["How are you?", "What's your favorite movie?"],
+    theme="soft"
+).launch()