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
8
Inference Examples
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.

Dataset used to train Den4ikAI/FRED-T5-XL-interpreter