Create app.py

app.py

@@ -0,0 +1,55 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+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 + " I'm here to help you relax. You can talk to me about anything that's on your mind or ask for relaxation tips."}]
+
+    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
+
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="Remember to breathe and take things one step at a time.", 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)"),
+    ],
+    examples=[
+        ["I'm feeling stressed about work."],
+        ["Can you give me a relaxation tip?"],
+        ["I need help winding down after a long day."]
+    ],
+    title="Calm Mate"  # Setting the title of the app
+)
+
+if __name__ == "__main__":
+    demo.launch()