SK_BPE_BLM

Slovak BPE Baby Language Model (SK_BPE_BLM)

SK_BPE_BLM is a pretrained small language model for the Slovak language, based on the RoBERTa architecture. The model utilizes standard Byte-Pair Encoding (BPE) tokenization (pureBPE, more info here) and is case-insensitive, meaning it operates in lowercase. While the pretrained model can be used for masked language modeling, it is primarily intended for fine-tuning on downstream NLP tasks.

How to Use the Model

To use the SK_BPE_BLM model, follow these steps:

from transformers import pipeline, RobertaTokenizer, AutoModelForMaskedLM

# Load the custom tokenizer and model
tokenizer = RobertaTokenizer.from_pretrained("daviddrzik/SK_BPE_BLM")
model = AutoModelForMaskedLM.from_pretrained("daviddrzik/SK_BPE_BLM")

# Create a pipeline with the custom model and tokenizer
unmasker = pipeline('fill-mask', model=model, tokenizer=tokenizer)

# Use the pipeline
result = unmasker("včera večer sme <mask> nový film v kine, ktorý mal premiéru iba pred týždňom.")
print(result)

[{'score': 0.2665567100048065,
  'token': 18599,
  'token_str': ' pozreli',
  'sequence': 'včera večer sme pozreli nový film v kine, ktorý mal premiéru iba pred týždňom.'},
 {'score': 0.23860174417495728,
  'token': 1056,
  'token_str': ' mali',
  'sequence': 'včera večer sme mali nový film v kine, ktorý mal premiéru iba pred týždňom.'},
 {'score': 0.1962040513753891,
  'token': 6915,
  'token_str': ' videli',
  'sequence': 'včera večer sme videli nový film v kine, ktorý mal premiéru iba pred týždňom.'},
 {'score': 0.03656836599111557,
  'token': 26996,
  'token_str': ' pozerali',
  'sequence': 'včera večer sme pozerali nový film v kine, ktorý mal premiéru iba pred týždňom.'},
 {'score': 0.030735589563846588,
  'token': 9058,
  'token_str': ' objavili',
  'sequence': 'včera večer sme objavili nový film v kine, ktorý mal premiéru iba pred týždňom.'}]

Training Data

The SK_BPE_BLM model was pretrained using a subset of the OSCAR 2019 corpus, specifically focusing on the Slovak language. The corpus underwent comprehensive preprocessing to ensure the quality and relevance of the data:

• Language Filtering: Non-Slovak text was removed to focus solely on the Slovak language.
• Character Normalization: Various types of spaces, quotes, dashes, and separators were standardized (e.g., replacing different types of spaces with a single space, or dashes with hyphens). Emoticons were replaced with spaces.
• Symbol and Unwanted Text Removal: Sentences containing mathematical symbols, pictograms, or characters from Asian and African languages were deleted. Duplicates of punctuation, special characters, and spaces were also removed.
• URL and Text Normalization: All web addresses were removed, and the text was converted to lowercase to simplify tokenization.
• Content Cleanup: Text that included irrelevant content from web crawling, such as keywords and HTML tags, was identified and removed.

Additionally, the preprocessing included further refinement steps to create the final dataset:

• Parentheses Content Removal: All content within parentheses was removed to reduce noise.
• Selection of Text Segments: Medium-length text paragraphs were selected to maintain consistency.
• Similarity Filtering: Paragraphs with at least 50% similarity to previous ones were removed to minimize redundancy.
• Random Sampling: Finally, 20% of the remaining paragraphs were randomly selected.

After preprocessing, the training corpus consisted of:

• 455 MB of text
• 895,125 paragraphs
• 64.6 million words
• 1.13 million unique words
• 119 unique characters

Pretraining

The SK_BPE_BLM model was trained with the following key parameters:

• Architecture: Based on RoBERTa, with 6 hidden layers and 12 attention heads.
• Hidden size: 576
• Vocabulary size: 50,264 tokens
• Sequence length: 256 tokens
• Dropout: 0.1
• Number of parameters: 58 million
• Optimizer: AdamW, learning rate 1×10^(-4), weight decay 0.01
• Training: 30 epochs, divided into 3 phases:
  • Phase 1: 10 epochs on CPU (4x AMD EPYC 7542), batch size 64, 50 hours per epoch, 139,870 steps total.
  • Phase 2: 5 epochs on GPU (1x Nvidia A100 40GB), batch size 64, 100 minutes per epoch, 69,935 steps total.
  • Phase 3: 15 epochs on GPU (2x Nvidia A100 40GB), batch size 128, 60 minutes per epoch, 104,910 steps total.

The model was trained using the Hugging Face library, but without using the Trainer class—native PyTorch was used instead.

Fine-Tuned Versions of the SK_BPE_BLM Model

Here are the fine-tuned versions of the SK_BPE_BLM model based on the folders provided:

• SK_BPE_BLM-ner: Fine-tuned for Named Entity Recognition (NER) tasks.
• SK_BPE_BLM-pos: Fine-tuned for Part-of-Speech (POS) tagging.
• SK_BPE_BLM-qa: Fine-tuned for Question Answering tasks.
• SK_BPE_BLM-sentiment-csfd: Fine-tuned for sentiment analysis on the CSFD (movie review) dataset.
• SK_BPE_BLM-sentiment-multidomain: Fine-tuned for sentiment analysis across multiple domains.
• SK_BPE_BLM-sentiment-reviews: Fine-tuned for sentiment analysis on general review datasets.
• SK_BPE_BLM-topic-news: Fine-tuned for topic classification in news articles.

Citation

If you find our model or paper useful, please consider citing our work:

Articles

Part of this research (specifically the models pre-trained for 10 epochs) has been published in:

Držík, D., & Forgac, F. (2024). Slovak morphological tokenizer using the Byte-Pair Encoding algorithm. PeerJ Computer Science, 10, e2465. https://doi.org/10.7717/peerj-cs.2465

An extended version of this work (including models pre-trained for 30 epochs and evaluated across multiple NLP downstream tasks) has been published in:

Držík, D., & Kapusta, J. (2026). The importance of morphology-aware subword tokenization for NLP tasks in Slovak language modeling. Expert Systems with Applications, 312, 131492. https://doi.org/10.1016/j.eswa.2026.131492

BibTeX entries

@article{drzik2024slovak,
  title={Slovak morphological tokenizer using the Byte-Pair Encoding algorithm},
  author={Držík, Dávid and Forgac, František},
  journal={PeerJ Computer Science},
  volume={10},
  pages={e2465},
  year={2024},
  month={11},
  issn={2376-5992},
  doi={10.7717/peerj-cs.2465}
}

@article{Drzik2026,
  author = {Dávid Držík and Jozef Kapusta},
  title = {The importance of morphology-aware subword tokenization for NLP tasks in Slovak language modeling},
  journal = {Expert Systems with Applications},
  volume = {312},
  pages = {131492},
  year = {2026},
  month = {5},
  issn = {09574174},
  doi = {10.1016/j.eswa.2026.131492}
}