mbart-large-50-sin-32768

This model is a 36.42% smaller version of facebook/mbart-large-50 optimized for Sinhala language via vocabulary size reduction using the trimming method.
This trimmed model should perform similarly to the original model with only 32,768 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected languages were removed from the vocabulary.

Model Statistics

Metric	Original	Trimmed	Reduction
Vocabulary size	250,054 tokens	32,768 tokens	86.90%
Model size	610,879,488 params	388,378,624 params	36.42%

Mining Dataset Statistics

• Number of texts used for mining: 200,000 texts
• Dataset: lbourdois/fineweb-2-trimming

Usage

from transformers import AutoModel, AutoTokenizer

model_name = "alphaedge-ai/mbart-large-50-sin-32768"
model = AutoModel.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Citations

mBART

@misc{tang2020multilingualtranslationextensiblemultilingual,
      title={Multilingual Translation with Extensible Multilingual Pretraining and Finetuning}, 
      author={Yuqing Tang and Chau Tran and Xian Li and Peng-Jen Chen and Naman Goyal and Vishrav Chaudhary and Jiatao Gu and Angela Fan},
      year={2020},
      eprint={2008.00401},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2008.00401}, 
}

Trimming blog post

@misc{hf_blogpost_trimming,
      title={Introduction to Trimming}, 
      author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
      year={2026},
      url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, 
}