TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking
This work addresses the problem of limited resources for Bangla language modeling, laying groundwork for adapting models to other low-resource languages, though it is incremental as it builds on existing multilingual models.
The authors tackled the lack of large pretrained language models for Bangla by developing TituLLMs in 1b and 3b parameter sizes, trained on ~37 billion tokens, and created five benchmarking datasets, showing that TituLLMs sometimes outperforms its initial multilingual versions but not always.
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).