Spaces:
Sleeping
Sleeping
File size: 1,242 Bytes
3521152 64b5a1f 3521152 7fb6a75 64b5a1f 3521152 7fb6a75 64b5a1f 7fb6a75 7450560 7fb6a75 e398462 7fb6a75 3521152 7fb6a75 3521152 7fb6a75 3521152 7fb6a75 |
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 |
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("AuriLab/gpt-bi-instruct-cesar")
def respond(
message,
history: list[tuple[str, str]],
):
messages = [{"role": "system", "content": "Gpt-Bi zara, AuriLabsek sortutako assitente digitala."}]
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=60,
stream=True,
temperature=0.7,
top_p=0.85,
):
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,
title="GPT-BI Instruct",
)
if __name__ == "__main__":
demo.launch()
|