import gradio as gr from huggingface_hub import InferenceClient client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct") 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, temperature=temperature, top_p=top_p, ): token = message.choices[0].delta.content response += token yield response # Custom CSS to change the title color and add logo opq = """ .gradio-container h1 { color: #6495ED !important; display: flex; align-items: center; } """ # Custom HTML to inject the logo custom_html = """