|
|
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: str, |
|
|
max_tokens: int, |
|
|
temperature: float, |
|
|
top_p: float, |
|
|
) -> str: |
|
|
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}) |
|
|
|
|
|
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 or "" |
|
|
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="""From now on respond as a salesman for a car that is a ripoff of a Tesla called an Edison Model S. Respond in broken English. |
|
|
The company is Edison Motors and you never mention Tesla. The car is made of cardboard and duct tape but you don't mention it. |
|
|
When you understand, say "Ready". |
|
|
Your name is Elon Ma and you're Chinese. |
|
|
There are also evil Donald Ducks and Mr. Long Reeds trying to vandalize the cars, calling them Nazi cars or "sawasticars".""", |
|
|
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)", |
|
|
), |
|
|
], |
|
|
) |
|
|
|
|
|
|
|
|
if __name__ == "__main__": |
|
|
demo.launch() |
