Қазақша. Ш. Шаяхметов атындағы «Тіл-Қазына» ұлттық ғылыми-практикалық орталығы қазақ тіліне арналған деректер мен модельдерді әзірлейді. Бұл парақта мәтін, сөйлеу, OCR, морфология, терминология және тілдік модель репозиторийлері жинақталған.

По-русски. Национальный научно-практический центр «Тіл-Қазына» имени Ш. Шаяхметова выпускает данные и модели для казахского языка. Здесь собраны репозитории текстов, речи, OCR, морфологии, терминологии и языковых моделей.

The National Scientific and Practical Centre 'Til-Qazyna' named after Sh. Shayakhmetov (Ш. Шаяхметов атындағы «Тіл-Қазына» ұлттық ғылыми-практикалық орталығы) develops datasets and models for Kazakh. Its repositories link source corpora, curated datasets, tokenizers, base models and task-specific fine-tunes, allowing researchers to trace training data and developers to work with the released resources.

What's here

The total includes all branches and revision history. Repository cards are available in Kazakh, Russian and English.

Flagship datasets

Model families

Til Core

Kazakh-only models trained from scratch with a 256,000-token morpheme-aware BPE vocabulary.

Til multilingual

Kazakh-first models covering Russian, English, code and mathematics with a 131,072-token vocabulary.

Til 256k research ladder

The exp080–exp085 sequence follows a Kazakh model through pretraining, instruction tuning and GEC.

Collections

• Til Flagship Datasets — datasets for pretraining, instruction tuning, speech and language tasks; 9 repositories.
• Til Core — Kazakh-only models — base, instruct and GEC models for Kazakh; 6 repositories.
• Til — multilingual models — Kazakh-first base models and task fine-tunes; 8 repositories.
• Kazakh GEC — all models — correction models and their training dataset; 8 repositories.
• Til 256k research ladder — checkpoints and data from the exp080–exp085 sequence; 6 repositories.
• Tokenizers — tokenizers and vocabulary data for model training; 2 repositories.
• Til Instruct — task datasets — instruction data for QA, summarization, classification and generation; 18 repositories.
• Til Books — sources and scans — extracted books, scans and source-specific subsets; 6 repositories.
• Til Web, crawls and archive — web text, crawls and archived sources for pretraining corpora; 11 repositories.
• Speech and OCR — audio data, ASR models and OCR tools; 6 repositories.
• Kazakh morphology and POS — models and annotated data for segmentation, morphology and POS tagging; 16 repositories.
• Kazakh terminology — terminology extraction models, datasets and evaluations; 9 repositories.
• First releases (2024) — early language and speech models; 3 repositories.

Start here

Run an instruction model

from transformers import pipeline
generate = pipeline("text-generation", model="TilQazyna/Til-2B-instruct")
print(generate("Қазақ тілінде қысқаша жауап бер:", max_new_tokens=80)[0]["generated_text"])

Stream the pretraining corpus

from datasets import load_dataset
ds = load_dataset("TilQazyna/Til-Corpus", "premium", split="train", streaming=True)
print(next(iter(ds)))

Prepare corpus records with the released tokenizer

from datasets import load_dataset
from transformers import AutoTokenizer
ds = load_dataset("TilQazyna/Til-Corpus", "premium", split="train", streaming=True)
tokenizer = AutoTokenizer.from_pretrained("TilQazyna/Til-Tokenizer-128k")
tokenized = ds.map(lambda row: tokenizer(row["text"], truncation=True))

Access

All repositories require access approval. Cards and file lists are public; files can be downloaded after the TilQazyna team approves a request submitted through Request access.

Citation

@misc{tilqazyna2026,
  author = {{Ш. Шаяхметов атындағы «Тіл-Қазына» ұлттық ғылыми-практикалық орталығы}},
  title = {Til-Qazyna on Hugging Face},
  year = {2026},
  url = {https://huggingface.co/TilQazyna}
}