Create app.py

app.py

@@ -0,0 +1,48 @@
+# app.py
+import gradio as gr
+from transformers import pipeline
+import torch
+
+# ====== Load Model ======
+device = 0 if torch.cuda.is_available() else -1
+pipe = pipeline(
+    "text-generation",
+    model="rahul7star/Qwen0.5-3B-Gita",
+    device=device,
+)
+
+# ====== Chat Function ======
+def chat_with_model(message, history):
+    """
+    message: new user message
+    history: list of (user, bot) pairs
+    """
+    # Build message history for the model
+    messages = [{"role": "system", "content": "You are a friendly assistant trained on Gita knowledge."}]
+    for user, bot in history:
+        messages.append({"role": "user", "content": user})
+        messages.append({"role": "assistant", "content": bot})
+    messages.append({"role": "user", "content": message})
+
+    # Generate reply
+    output = pipe(messages, max_new_tokens=200, do_sample=True, temperature=0.7)
+    reply = output[0]['generated_text'][-1]['content'] if isinstance(output[0]['generated_text'], list) else output[0]['generated_text']
+
+    # Update history
+    history.append((message, reply))
+    return "", history
+
+# ====== Gradio Interface ======
+with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue")) as demo:
+    gr.Markdown("## 💬 Qwen0.5-3B-Gita — Conversational Assistant")
+
+    chatbot = gr.Chatbot(height=500)
+    msg = gr.Textbox(placeholder="Ask about the Gita, life, or philosophy...", label="Your Message")
+    clear = gr.Button("Clear")
+
+    msg.submit(chat_with_model, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+# ====== Launch ======
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)