---
language:
- tr
arXiv: 2403.01308
library_name: transformers
pipeline_tag: text2text-generation
license: cc-by-nc-sa-4.0
inference: false
datasets:
- vngrs-ai/vngrs-web-corpus
---
# VBART Model Card

## Model Description  

VBART is the first sequence-to-sequence LLM pre-trained on Turkish corpora from scratch on a large scale. It was pre-trained by VNGRS in February 2023.  
The model is capable of conditional text generation tasks such as text summarization, paraphrasing, and title generation when fine-tuned.
It outperforms its multilingual counterparts, albeit being much smaller than other implementations.

This repository contains pre-trained TensorFlow and Safetensors weights of VBART-Medium-Base.

- **Developed by:** [VNGRS-AI](https://vngrs.com/ai/)
- **Model type:**  Transformer encoder-decoder based on mBART architecture
- **Language(s) (NLP):** Turkish
- **License:** CC BY-NC-SA 4.0
- **Paper:** [arXiv](https://arxiv.org/abs/2403.01308)

## Training Details  

### Training Data  
The base model is pre-trained on [vngrs-web-corpus](https://huggingface.co/datasets/vngrs-ai/vngrs-web-corpus). It is curated by cleaning and filtering Turkish parts of [OSCAR-2201](https://huggingface.co/datasets/oscar-corpus/OSCAR-2201) and [mC4](https://huggingface.co/datasets/mc4) datasets. These datasets consist of documents of unstructured web crawl data. More information about the dataset can be found on their respective pages. Data is filtered using a set of heuristics and certain rules, explained in the appendix of our [paper](https://arxiv.org/abs/2403.01308).

### Limitations
This model is the pre-trained base model and is capable of masked language modeling.
Its purpose is to serve as the base model to be fine-tuned for downstream tasks.

### Training Procedure  
Pre-trained for a total of 63B tokens.
#### Hardware
- **GPUs**: 8 x Nvidia A100-80 GB
#### Software
- TensorFlow
#### Hyperparameters  
##### Pretraining
- **Training regime:** fp16 mixed precision
- **Training objective**: Span masking (using mask lengths sampled from Poisson distribution λ=3.5, masking 30% of tokens)
- **Optimizer** : Adam optimizer (β1 = 0.9, β2 = 0.98, Ɛ = 1e-6)
- **Scheduler**: Custom scheduler from the original Transformers paper (20,000 warm-up steps)
- **Dropout**: 0.1
- **Initial Learning rate**: 5e-6
- **Training tokens**: 63B


## Citation  
```
@article{turker2024vbart,
  title={VBART: The Turkish LLM},
  author={Turker, Meliksah and Ari, Erdi and Han, Aydin},
  journal={arXiv preprint arXiv:2403.01308},
  year={2024}
}
```