sr-gpt2 / README.md
elishowk's picture
Automatic correction of README.md metadata for keys. Contact website@huggingface.co for any question
728a90e
metadata
language:
  - sr
thumbnail: https://huggingface.co/macedonizer/sr-gpt2/desanka-maksimovic.jpeg
license: apache-2.0
datasets:
  - wiki-sr

sr-gpt2

Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in this paper and first released at this page.

Model description

sr-gpt2 is a transformers model pretrained on a very large corpus of Serbian data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labeling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences. More precisely, inputs are sequences of the continuous text of a certain length and the targets are the same sequence, shifted one token (word or piece of the word) to the right. The model uses internally a mask-mechanism to make sure the predictions for the token i only uses the inputs from 1 to i but not the future tokens. This way, the model learns an inner representation of the Macedonian language that can then be used to extract features useful for downstream tasks. The model is best at what it was pretrained for, however, which is generating texts from a prompt.

How to use

Here is how to use this model to get the features of a given text in PyTorch:

import random
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained('macedonizer/sr-gpt2')
model = AutoModelWithLMHead.from_pretrained('macedonizer/sr-gpt2')

input_text = 'Ја сам био '

if len(input_text) == 0:
encoded_input = tokenizer(input_text, return_tensors="pt")
output = model.generate(
bos_token_id=random.randint(1, 50000),
do_sample=True,
top_k=50,
max_length=1024,
top_p=0.95,
num_return_sequences=1,
)
else:
encoded_input = tokenizer(input_text, return_tensors="pt")
output = model.generate(
**encoded_input,
bos_token_id=random.randint(1, 50000),
do_sample=True,
top_k=50,
max_length=1024,
top_p=0.95,
num_return_sequences=1,
)

decoded_output = []
for sample in output:
decoded_output.append(tokenizer.decode(sample, skip_special_tokens=True))

print(decoded_output)