README.md

metadata

license: cc-by-sa-4.0
datasets:
  - procesaur/ZNANJE
  - procesaur/STARS
  - procesaur/Vikipedija
  - procesaur/Vikizvornik
  - jerteh/SrpELTeC
  - procesaur/kisobran
language:
  - sr
  - hr
base_model:
  - FacebookAI/xlm-roberta-large

TeslaXLM
Вишејезични модел, 561 милион параметара Обучаван над корпусима српског и српскохрватског језика - 20 милијарди речи Једнака подршка уноса на ћирилици и латиници!	Multilingual model, 561 million parameters Trained on Serbian and Serbo-Croatian corpora - 20 billion words Equal support for Cyrillic and Latin input!

>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='te-sla/teslaXLM')
>>> unmasker("Kada bi čovek znao gde će pasti on bi<mask>.")

>>> from transformers import AutoTokenizer, AutoModelForMaskedLM
>>> from torch import LongTensor, no_grad
>>> from scipy import spatial
>>> tokenizer = AutoTokenizer.from_pretrained('te-sla/teslaXLM')
>>> model = AutoModelForMaskedLM.from_pretrained('te-sla/teslaXLM', output_hidden_states=True)
>>> x = " pas"
>>> y = " mačka"
>>> z = " svemir"
>>> tensor_x = LongTensor(tokenizer.encode(x, add_special_tokens=False)).unsqueeze(0)
>>> tensor_y = LongTensor(tokenizer.encode(y, add_special_tokens=False)).unsqueeze(0)
>>> tensor_z = LongTensor(tokenizer.encode(z, add_special_tokens=False)).unsqueeze(0)
>>> model.eval()
>>> with no_grad():
>>>     vektor_x = model(input_ids=tensor_x).hidden_states[-1].squeeze()
>>>     vektor_y = model(input_ids=tensor_y).hidden_states[-1].squeeze()
>>>     vektor_z = model(input_ids=tensor_z).hidden_states[-1].squeeze()
>>>     print(spatial.distance.cosine(vektor_x, vektor_y))
>>>     print(spatial.distance.cosine(vektor_x, vektor_z))

Евалуација XLMR модела за српски језик	Serbian XLMR models evaluation results

Author

Mihailo Škorić

@procesaur

Author

Saša Petalinkar

@tanor

Computation

TESLA project

@te-sla

Cit.

@inproceedings{skoricxlm,
  author    = {Mihailo Škorić, Saša Petalinkar},
  title     = {New XLM-R-based language models for Serbian and Serbo-Croatian},
  booktitle   = {ARTIFICAL INTELLIGENCE CONFERENCE},
  year      = {2024},
  address = {Belgrade}
  publisher = {SASA, Belgrade},
  url       = {}
}

Истраживање jе спроведено уз подршку Фонда за науку Републике Србиjе, #7276, Text Embeddings – Serbian Language Applications – TESLA

This research was supported by the Science Fund of the Republic of Serbia, #7276, Text Embeddings - Serbian Language Applications - TESLA