changes

app.py

@@ -1,64 +1,55 @@
 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,
+# Initialize the inference client for AraT5
+# Make sure you have HF_TOKEN in your environment if the model requires auth
+client = InferenceClient(model="UBC-NLP/AraT5v2-base-1024")
+
+def format_history(history, user_message, system_message):
+    """
+    Format chat history into a single T5-style input string.
+    AraT5 is not a chat model, so we need to combine conversation turns into plain text.
+    """
+    conversation = f"system: {system_message}\n"
+    for user, bot in history:
+        if user:
+            conversation += f"user: {user}\n"
+        if bot:
+            conversation += f"assistant: {bot}\n"
+    conversation += f"user: {user_message}\nassistant:"
+    return conversation
+
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    """
+    Handle user input, format it for AraT5, and get a generated response.
+    """
+    # Format the history into one text prompt
+    prompt = format_history(history, message, system_message)
+
+    # Stream the model's output
+    response_text = ""
+    for chunk in client.text_generation(
+        prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
+        repetition_penalty=1.1
     ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        token = chunk.token.text
+        response_text += token
+        yield response_text
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create the Gradio Chat Interface
 demo = gr.ChatInterface(
-    respond,
+    fn=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.Textbox(value="أنت مساعد ذكي تجيب باللغة العربية.", label="System message"),
+        gr.Slider(minimum=1, maximum=512, value=256, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()