File size: 1,637 Bytes
c3dfc09 dfa1a47 c3dfc09 dfa1a47 ca1d8ee dfa1a47 c3dfc09 ca1d8ee c3dfc09 dfa1a47 c3dfc09 ca1d8ee c3dfc09 dfa1a47 8d3c493 dfa1a47 8d3c493 dfa1a47 143ddd8 dfa1a47 e1f2405 ca1d8ee dfa1a47 ca1d8ee c3dfc09 ca1d8ee c3dfc09 ca1d8ee |
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 |
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
# Подключаем модель и токенизатор
model_name = "distilgpt2"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
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})
input_text = "\n".join([msg["content"] for msg in messages])
inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True)
outputs = model.generate(
inputs["input_ids"],
max_length=max_tokens,
temperature=temperature,
top_p=top_p,
do_sample=True,
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
response += "\nСделано больницей EMS штата Alta!"
return response
# Интерфейс Gradio
demo = gr.Interface(
fn=respond,
inputs=[
gr.Textbox(value="Здравствуйте. Отвечай кратко...", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, label="Max Tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, label="Top-p"),
],
outputs="text",
)
demo.launch()
|