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") | |
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 | |
""" | |
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: | |
gr.Markdown("## Zephyr Chatbot with Custom UI") | |
chatbot = gr.Chatbot() | |
state = gr.State([]) | |
with gr.Row(): | |
msg = gr.Textbox(label="Type your message...", scale=6) | |
send_btn = gr.Button("Send", scale=1) | |
role_dropdown = gr.Dropdown(choices=["SDE", "BA"], label="Select Role", value="SDE") | |
system = gr.Textbox(value="You are a friendly chatbot.", label="System message") | |
max_tokens = gr.Slider(1, 2048, value=512, label="Max tokens") | |
temperature = gr.Slider(0.1, 4.0, value=0.7, label="Temperature", step=0.1) | |
top_p = gr.Slider(0.1, 1.0, value=0.95, label="Top-p", step=0.05) | |
with gr.Row(): | |
clear_btn = gr.Button("Clear Chat") | |
dummy_btn = gr.Button("Dummy Action") | |
def handle_submit(message, history, system, max_tokens, temperature, top_p): | |
response_gen = response(message, history, system, max_tokens, temperature, top_p) | |
final_response = "" | |
for r in response_gen: | |
final_response = r | |
updated_history = history + [(message, final_response)] | |
return updated_history, updated_history, "" | |
send_btn.click( | |
handle_submit, | |
[msg, state, system, max_tokens, temperature, top_p], | |
[chatbot, state, msg], | |
) | |
msg.submit( | |
handle_submit, | |
[msg, state, system, max_tokens, temperature, top_p], | |
[chatbot, state, msg], | |
) | |
clear_btn.click(lambda: ([], [], ""), None, [chatbot, state, msg]) | |
dummy_btn.click(lambda: gr.Info("Dummy action clicked!"), None, None) | |
if __name__ == "__main__": | |
demo.launch() | |