KazBERT

KazBERT is a BERT-based model specifically designed and fine-tuned for Kazakh language tasks. The model is trained using Masked Language Modeling (MLM) on a multilingual text corpus containing Kazakh, Russian, and English texts.

Features

• Custom tokenizer optimized for Kazakh language
• Trained on diverse Kazakh text corpus
• Supports downstream NLP tasks for Kazakh

View on Hugging Face