# Towards Nepali-language LLMs: Efficient GPT training with a Nepali BPE tokenizer

arXiv: https://arxiv.org/abs/2512.14585 · HTML: https://mlsanity.com/paper/2512.14585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [FlauBERT: Unsupervised Language Model Pre-training for French](https://mlsanity.com/paper/1912.05372/) (2019)
- [German's Next Language Model](https://mlsanity.com/paper/2010.10906/) (2020)
- [A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages](https://mlsanity.com/paper/2006.06202/) (2020)
- [Multilingual is not enough: BERT for Finnish](https://mlsanity.com/paper/1912.07076/) (2019)
- [Development of Pre-Trained Transformer-based Models for the Nepali Language](https://mlsanity.com/paper/2411.15734/) (2024)

## Abstract (arXiv)

Nepali, a low-resource language spoken by over 32 million people, continues to face challenges in natural language processing (NLP) due to its complex grammar, agglutinative morphology, and limited availability of high-quality corpora. Most efforts to date have centered on basic encoder architectures; they remain insufficient for Nepali-specific text generation. This study presents a GPT-2-based Nepali language model trained using several training strategies inspired by GPT-3, including optimized learning rate schedules, batch scaling, and architectural refinements. A custom 16k Byte-Pair Encoding (BPE) tokenizer was trained exclusively on Nepali text to ensure more consistent segmentation and improved input representation. The model was pretrained on a combined dataset comprising a 10.75GB cleaned NepBERTa corpus and additional web-scraped Nepali news articles. FlashAttention was integrated to reduce memory usage and stabilize training. After two epochs, the model achieved a training loss of 3.168177, a validation loss of 3.081982, and a final perplexity of 21.80, demonstrating its capability to generate coherent Nepali news-style text.