Edit model card

Den4ikAI/FRED-T5-XL_instructor

Инструкционная модель на FRED-T5-XL.

Пример использования

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch
use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
tokenizer = AutoTokenizer.from_pretrained("Den4ikAI/FRED-T5-XL_instructor")
model = AutoModelForSeq2SeqLM.from_pretrained("Den4ikAI/FRED-T5-XL_instructor", torch_dtype=torch.float16).to(device)
model.eval()

from transformers import GenerationConfig

generation_config = GenerationConfig.from_pretrained("Den4ikAI/FRED-T5-XL_instructor")
def generate(prompt):
  data = tokenizer(f"<SC6>Человек: {prompt}\nБот: <extra_id_0>", return_tensors="pt").to(model.device)
  output_ids = model.generate(
      **data,
      generation_config=generation_config
  )[0]
  out = tokenizer.decode(output_ids.tolist())
  return out

while 1:
  print(generate(input(":> ")))

Citation

@MISC{Den4ikAI/FRED-T5-XL_instructor,
    author  = {Denis Petrov},
    title   = {Russian Instructor Model},
    url     = {https://huggingface.co/Den4ikAI/FRED-T5-XL_instructor/},
    year    = 2023
}
Downloads last month
16
Safetensors
Model size
1.74B params
Tensor type
BF16
·
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.