File size: 1,399 Bytes
c14a211 6cbf875 c14a211 6cbf875 c14a211 6cbf875 c14a211 |
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 AutoTokenizer, AutoModelForCausalLM
import torch
# Установка сида для воспроизводимости
torch.manual_seed(42)
model_id = "t-tech/T-lite-it-1.0"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto"
)
def generate_response(prompt):
messages = [
{"role": "system", "content": "Ты T-lite, виртуальный ассистент в Т-Технологии. Твоя задача - быть полезным диалоговым ассистентом."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=256
)
generated_ids = [
output_ids[len(input_ids):]
for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
return response
interface = gr.Interface(
fn=generate_response,
inputs="text",
outputs="text",
title="T-lite API"
)
interface.launch() |