File size: 1,901 Bytes
42192c3 aa2c59f 42192c3 fa681c6 b4b5a03 42192c3 426e7fc 42192c3 5d90af7 42192c3 ee99f3e 42192c3 5d90af7 42192c3 e22de59 42192c3 5be3161 42192c3 85e53ab |
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 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
Cloned from https://huggingface.co/spaces/gradio-templates/chatbot - and added the history toggle to the interface
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("kolbeins/model")
def respond(
message,
history: list[tuple[str, str]],
system_message,
use_history,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
# Only use history if the toggle is on
if use_history == "Yes":
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
# Then add to history (even if the toggle is of)
history.append((message, response))
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Radio(["Yes", "No"], value="Yes", label="Use chat history"),
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()
|