Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from huggingface_hub import InferenceClient | |
| """ | |
| For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference | |
| """ | |
| client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") | |
| SYSTEM_MAGIC = """ | |
| Your container is written in HTML. All outputs must be in HTML format. User cannot see what you say unles it is in HTML. | |
| <!DOCTYPE html>""" | |
| def respond(message): | |
| messages = [{"role": "system", "content": SYSTEM_MAGIC}] | |
| messages.append({"role": "user", "content": message}) | |
| response = "" | |
| for message in client.chat_completion( | |
| messages, | |
| max_tokens=4096, | |
| stream=True, | |
| temperature=0.248, | |
| top_p=0.842, | |
| ): | |
| token = message.choices[0].delta.content | |
| response += token | |
| yield response | |
| print(response) | |
| return response | |
| """ | |
| For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface | |
| """ | |
| #demo = gr.ChatInterface( | |
| # respond, | |
| ## additional_inputs=[ | |
| # gr.Textbox(value="You are a friendly Chatbot.", 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)", | |
| # ), | |
| # ], | |
| #) | |
| with gr.Blocks() as demo: | |
| with gr.Row(): | |
| hml = gr.HTML("") | |
| with gr.Row(): | |
| tb = gr.Textbox(placeholder="Your input here...") | |
| with gr.Row(): | |
| bn = gr.Button("Submit") | |
| bn.click(respond, inputs=[tb], outputs=[hml]) | |
| if __name__ == "__main__": | |
| demo.launch() |