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 fine-tuned TensorFlow and Safetensors weights of VBART for text summarization task.
- Developed by: VNGRS-AI
- Model type: Transformer encoder-decoder based on mBART architecture
- Language(s) (NLP): Turkish
- License: CC BY-NC-SA 4.0
- Finetuned from: VBART-Large
- Paper: arXiv
How to Get Started with the Model
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("vngrs-ai/VBART-Large-Summarization",
model_input_names=['input_ids', 'attention_mask'])
# Uncomment the device_map kwarg and delete the closing bracket to use model for inference on GPU
model = AutoModelForSeq2SeqLM.from_pretrained("vngrs-ai/VBART-Large-Summarization")#, device_map="auto")
input_text="..."
token_input = tokenizer(input_text, return_tensors="pt")#.to('cuda')
outputs = model.generate(**token_input)
print(tokenizer.decode(outputs[0]))
Training Details
Training Data
The base model is pre-trained on vngrs-web-corpus. It is curated by cleaning and filtering Turkish parts of OSCAR-2201 and 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.
The fine-tuning dataset is the Turkish sections of MLSum, TRNews, XLSum and Wikilingua datasets.
Limitations
This model is fine-tuned for paraphrasing tasks. It is not intended to be used in any other case and can not be fine-tuned to any other task with full performance of the base model. It is also not guaranteed that this model will work without specified prompts.
Training Procedure
Pre-trained for 30 days and for a total of 708B tokens. Finetuned for 30 epoch.
Hardware
- GPUs: 8 x Nvidia A100-80 GB
Software
- TensorFlow
Hyperparameters
Pretraining
- Training regime: fp16 mixed precision
- Training objective: Sentence permutation and 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 (dropped to 0.05 and then to 0 in the last 165k and 205k steps, respectively)
- Initial Learning rate: 5e-6
- Training tokens: 708B
Fine-tuning
- Training regime: fp16 mixed precision
- Optimizer : Adam optimizer (β1 = 0.9, β2 = 0.98, Ɛ = 1e-6)
- Scheduler: Linear decay scheduler
- Dropout: 0.1
- Learning rate: 1e-5
- Fine-tune epochs: 20
Metrics
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}
}