Legal T5 Small Trans Fr Es

🚀 legal_t5_small_trans_fr_es Model

A model designed for translating legal text from French to Spanish, offering efficient and accurate translation services.

🚀 Quick Start

The legal_t5_small_trans_fr_es model is tailored for translating legal text from French to Spanish. It was initially released in this repository and trained on three parallel corpora from JRC-ACQUIS, Europarl, and DCEP.

✨ Features

• Based on t5-small: The model is built upon the t5-small architecture, with a scaled - down baseline model. It uses dmodel = 512, dff = 2,048, 8 - headed attention, and only 6 layers each in the encoder and decoder, resulting in about 60 million parameters.
• Trained on Multiple Datasets: It was trained on [JRC - ACQUIS](https://wt - public.emm4u.eu/Acquis/index_2.2.html), EUROPARL, and [DCEP](https://ec.europa.eu/jrc/en/language - technologies/dcep) datasets, which consist of 5 Million parallel texts.

📦 Installation

There is no specific installation step provided in the original document.

💻 Usage Examples

Basic Usage

Here is how to use this model to translate legal text from French to Spanish in PyTorch:

from transformers import AutoTokenizer, AutoModelWithLMHead, TranslationPipeline

pipeline = TranslationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/legal_t5_small_trans_fr_es"),
tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/legal_t5_small_trans_fr_es", do_lower_case=False, 
                                            skip_special_tokens=True),
    device=0
)

fr_text = "commission des libertés civiles, de la justice et des affaires intérieures"

pipeline([fr_text], max_length=512)

📚 Documentation

Intended uses & limitations

The model could be used for translation of legal texts from French to Spanish.

Training data

The legal_t5_small_trans_fr_es model was trained on [JRC - ACQUIS](https://wt - public.emm4u.eu/Acquis/index_2.2.html), EUROPARL, and [DCEP](https://ec.europa.eu/jrc/en/language - technologies/dcep) dataset consisting of 5 Million parallel texts.

Training procedure

• Overall Training: The model was trained on a single TPU Pod V3 - 8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder - decoder architecture.
• Optimizer: The optimizer used is AdaFactor with inverse square root learning rate schedule for pre - training.
• Preprocessing: An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.

Evaluation results

When the model is used for translation test dataset, it achieves the following results:

🔧 Technical Details

The model is based on the t5 - small model. It scales down the baseline model of t5 by using dmodel = 512, dff = 2,048, 8 - headed attention, and only 6 layers each in the encoder and decoder. This variant has about 60 million parameters.

📄 License

There is no license information provided in the original document.

BibTeX entry and citation info

Created by Ahmed Elnaggar/@Elnaggar_AI | [LinkedIn](https://www.linkedin.com/in/prof - ahmed - elnaggar/)