Natsumi / app.py
Grayjack's picture
Update app.py
a068f00 verified
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("Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2")
def respond(
message,
history: list[dict],
system_message,
max_tokens,
temperature,
top_p,
):
# Start with the system message
messages = [{"role": "system", "content": system_message}]
# Convert the history to the new format
for val in history:
messages.append({"role": "user", "content": val['user']})
messages.append({"role": "assistant", "content": val['assistant']})
# Append the latest user message
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 Natsumi.", 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()