Yuvanesh123/Code_assistant_llm

1import gradio as gr2from huggingface_hub import InferenceClient3 4"""5For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference6"""7client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")8 9 10def respond(11    message,12    history: list[tuple[str, str]],13    system_message,14    max_tokens,15    temperature,16    top_p,17):18    messages = [{"role": "system", "content": system_message}]19 20    for val in history:21        if val[0]:22            messages.append({"role": "user", "content": val[0]})23        if val[1]:24            messages.append({"role": "assistant", "content": val[1]})25 26    messages.append({"role": "user", "content": message})27 28    response = ""29 30    for message in client.chat_completion(31        messages,32        max_tokens=max_tokens,33        stream=True,34        temperature=temperature,35        top_p=top_p,36    ):37        token = message.choices[0].delta.content38 39        response += token40        yield response41 42 43"""44For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface45"""46demo = gr.ChatInterface(47    respond,48    additional_inputs=[49        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),50        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),51        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),52        gr.Slider(53            minimum=0.1,54            maximum=1.0,55            value=0.95,56            step=0.05,57            label="Top-p (nucleus sampling)",58        ),59    ],60)61 62 63if __name__ == "__main__":64    demo.launch()65