Spaces:
Sleeping
Sleeping
File size: 1,865 Bytes
be0bcf5 0ec1a97 8ac3288 e091083 0ec1a97 e091083 0ec1a97 e091083 bd7ac30 8ac3288 bd7ac30 e091083 bd7ac30 e091083 |
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 |
import os
import gradio as gr
from huggingface_hub import InferenceClient
# Используем токен из secrets
client = InferenceClient(os.getenv("HUGGINGFACE_TOKEN"))
def respond(
message,
history: list[tuple[str, str]],
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 = ""
try:
# Указываем модель
for message in client.chat_completion(
model="sambanovasystems/SambaLingo-Russian-Chat",
messages=messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
except Exception as e:
print(f"Error: {e}")
yield "Произошла ошибка при обработке вашего запроса."
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="Ты дружелюбный чат-бот.", label="Системное сообщение"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Максимум новых токенов"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Температура"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch()
|