Create main.py

main.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+# Initialize the Hugging Face Inference Client
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    """
+    Handles user input and generates a response using the Hugging Face model.
+    """
+    try:
+        # Construct the conversation context
+        messages = [{"role": "system", "content": system_message}]
+        for user_msg, assistant_msg in history:
+            if user_msg:
+                messages.append({"role": "user", "content": user_msg})
+            if assistant_msg:
+                messages.append({"role": "assistant", "content": assistant_msg})
+        messages.append({"role": "user", "content": message})
+
+        # Generate the response
+        response = ""
+        for message in client.chat_completion(
+            messages, 
+            max_tokens=max_tokens, 
+            temperature=temperature, 
+            top_p=top_p, 
+            stream=True
+        ):
+            token = message.choices[0].delta.content
+            response += token
+            yield response
+    except Exception as e:
+        yield f"Error: {str(e)}"
+
+# Create the Gradio interface
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a helpful assistant.", label="System Message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, label="Max Tokens"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, label="Top-p (Nucleus Sampling)"),
+    ]
+)
+
+# Launch the app
+if __name__ == "__main__":
+    demo.launch()