Create app.py

app.py

@@ -0,0 +1,76 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
+import torch
+import threading
+
+# Load model
+model_name = "Qwen/Qwen3Guard-Gen-8B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+# Streaming response function
+def chat_with_dudea(message, history):
+    messages = [{"role": "system", "content": "You are DUDEAIBeta1.1, a fun and smart AI assistant."}]
+    for user_msg, bot_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        if bot_msg:
+            messages.append({"role": "assistant", "content": bot_msg})
+    messages.append({"role": "user", "content": message})
+
+    inputs = tokenizer.apply_chat_template(
+        messages,
+        add_generation_prompt=True,
+        tokenize=True,
+        return_dict=True,
+        return_tensors="pt"
+    ).to(model.device)
+
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    generation_kwargs = dict(inputs, max_new_tokens=250, streamer=streamer)
+    thread = threading.Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+
+    partial_response = ""
+    for new_text in streamer:
+        partial_response += new_text
+        yield partial_response
+
+# Custom UI
+with gr.Blocks(css="""
+    #chatbox {height: 600px; overflow-y: auto;}
+    .message {display: flex; align-items: flex-start; margin: 10px;}
+    .user {flex-direction: row-reverse;}
+    .avatar {width: 50px; height: 50px; border-radius: 50%; margin: 5px;}
+    .bubble {padding: 12px 16px; border-radius: 16px; max-width: 70%;}
+    .user .bubble {background-color: #4f46e5; color: white; border-bottom-right-radius: 4px;}
+    .bot .bubble {background-color: #f3f4f6; color: black; border-bottom-left-radius: 4px;}
+""") as demo:
+    gr.Markdown(
+        "<h1 style='text-align: center;'>🤖 DUDEAIBeta1.1</h1>"
+        "<p style='text-align:center;'>Next-gen AI with live typing ✨</p>"
+    )
+
+    # 👇 put your avatar files in the Space repo (user.png, ai.png)
+    chatbot = gr.Chatbot(
+        elem_id="chatbox",
+        avatar_images=("user.png", "ai.png")  # first is USER, second is AI
+    )
+
+    msg = gr.Textbox(placeholder="Type your message...", container=False)
+    clear = gr.Button("🧹 Clear Chat")
+
+    def respond(message, history):
+        response_stream = chat_with_dudea(message, history)
+        history.append((message, ""))
+        for partial in response_stream:
+            history[-1] = (message, partial)
+            yield "", history
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+demo.launch()