TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nahin, Shahriar Kabir, Nandi, Rabindra Nath, Sarker, Sagor, Muhtaseem, Quazi Sarwar, Kowsher, Md, Shill, Apu Chandraw, Ibrahim, Md, Menon, Mehadi Hasan, Muntasir, Tareq Al, Alam, Firoj
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908395753177088
author Nahin, Shahriar Kabir
Nandi, Rabindra Nath
Sarker, Sagor
Muhtaseem, Quazi Sarwar
Kowsher, Md
Shill, Apu Chandraw
Ibrahim, Md
Menon, Mehadi Hasan
Muntasir, Tareq Al
Alam, Firoj
author_facet Nahin, Shahriar Kabir
Nandi, Rabindra Nath
Sarker, Sagor
Muhtaseem, Quazi Sarwar
Kowsher, Md
Shill, Apu Chandraw
Ibrahim, Md
Menon, Mehadi Hasan
Muntasir, Tareq Al
Alam, Firoj
contents 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 languages. To facilitate broader adoption and further research, we have made the TituLLMs models and benchmarking datasets publicly available (https://huggingface.co/collections/hishab/titulm-llama-family-6718d31fc1b83529276f490a).
format Preprint
id arxiv_https___arxiv_org_abs_2502_11187
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking
Nahin, Shahriar Kabir
Nandi, Rabindra Nath
Sarker, Sagor
Muhtaseem, Quazi Sarwar
Kowsher, Md
Shill, Apu Chandraw
Ibrahim, Md
Menon, Mehadi Hasan
Muntasir, Tareq Al
Alam, Firoj
Computation and Language
Artificial Intelligence
68T50
F.2.2; I.2.7
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 languages. To facilitate broader adoption and further research, we have made the TituLLMs models and benchmarking datasets publicly available (https://huggingface.co/collections/hishab/titulm-llama-family-6718d31fc1b83529276f490a).
title TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking
topic Computation and Language
Artificial Intelligence
68T50
F.2.2; I.2.7
url https://arxiv.org/abs/2502.11187