Den4ikAI/FRED-T5-XL-interpreter
Модель для восстановления фразы с помощью контекста диалога (анафора, эллипсисы, гэппинг), проверки орфографии и нормализации текста диалоговых реплик.
Больше о задаче тут.
Пример использования
import torch
from transformers import T5ForConditionalGeneration, GPT2Tokenizer
model_name = 'Den4ikAI/FRED-T5-XL-interpreter'
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = T5ForConditionalGeneration.from_pretrained(model_name)
model.eval()
t5_input = '''<SC1>- Ты собак любишь?
- Не люблю я их
Развернутый ответ: <extra_id_0>'''
input_ids = tokenizer(t5_input, return_tensors='pt').input_ids
out_ids = model.generate(input_ids=input_ids, max_length=100, eos_token_id=tokenizer.eos_token_id, early_stopping=True)
t5_output = tokenizer.decode(out_ids[0][1:])
print(t5_output)
Citation
@MISC{FRED-T5-XL-interpeter,
author = {Denis Petrov, Ilya Koziev},
title = {Russian conversations interpreter and normalizer},
url = {https://huggingface.co./Den4ikAI/FRED-T5-XL-interpreter},
year = 2023
}
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.