TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking
Shahriar Kabir Nahin, Rabindra Nath Nandi, Sagor Sarker, Quazi Sarwar Muhtaseem, Md Kowsher, Apu Chandraw Shill, Md Ibrahim, Mehadi Hasan Menon, Tareq Al Muntasir, Firoj Alam

TL;DR
This paper introduces TituLLMs, the first large pretrained Bangla language models, along with comprehensive benchmarking datasets, demonstrating their performance and laying the foundation for low-resource language adaptation.
Contribution
We developed TituLLMs, the first Bangla LLMs, and created benchmarking datasets to evaluate their performance, facilitating research in low-resource language modeling.
Findings
TituLLMs outperform initial multilingual models in Bangla tasks.
Benchmarking datasets reveal language adaptation complexities.
Models and datasets are publicly available for research.
Abstract
In this paper, we present TituLLMs, the first large pretrained Bangla LLMs, available in 1b and 3b parameter sizes. Due to computational constraints during both training and inference, we focused on smaller models. To train TituLLMs, we collected a pretraining dataset of approximately ~37 billion tokens. We extended the Llama-3.2 tokenizer to incorporate language- and culture-specific knowledge, which also enables faster training and inference. There was a lack of benchmarking datasets to benchmark LLMs for Bangla. To address this gap, we developed five benchmarking datasets. We benchmarked various LLMs, including TituLLMs, and demonstrated that TituLLMs outperforms its initial multilingual versions. However, this is not always the case, highlighting the complexities of language adaptation. Our work lays the groundwork for adapting existing multilingual open models to other low-resource…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
- 🤗hishab/titulm-llama-3.2-1b-v1.1model· 15 dl· ♡ 115 dl♡ 1
- 🤗hishab/titulm-llama-3.2-3b-v1.0model· 2 dl2 dl
- 🤗hishab/titulm-llama-3.2-3b-v2.0model· 418 dl· ♡ 6418 dl♡ 6
- 🤗RichardErkhov/hishab_-_titulm-llama-3.2-3b-v2.0-4bitsmodel
- 🤗RichardErkhov/hishab_-_titulm-llama-3.2-3b-v2.0-8bitsmodel
- 🤗ashfaqfardin/titulm-llama-3.2-1b-v1.1-GGUFmodel· 12 dl12 dl
- 🤗ashfaqfardin/titulm-llama-3.2-3b-v2.0-GGUFmodel
- 🤗geekym15/titulm-llama-3.2-3b-v2.0-GGUFmodel
Videos
Taxonomy
TopicsAdvanced Data Storage Technologies · Data Mining Algorithms and Applications · Advanced Computational Techniques and Applications
