File size: 1,325 Bytes
47f155f 0bbac0a 47f155f 0bbac0a 47f155f 0bbac0a 47f155f 0bbac0a 47f155f 5421427 47f155f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def respond(message, history, 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
demo = gr.ChatInterface(
fn=respond,
additional_inputs=[
gr.Textbox(lines=2, label="System Message", placeholder="You are a helpful assistant."),
gr.Slider(0, 1024, value=256, step=1, label="Max Tokens"),
gr.Slider(0, 1, value=0.7, step=0.01, label="Temperature"),
gr.Slider(0, 1, value=0.9, step=0.01, label="Top-p")
],
title="Chat with Zephyr-7b",
description="Chatbot powered by Hugging Face Inference API."
)
demo.launch() # Remove or set share=False
|