# Sequence generation

OpenBA is an open-source 15-billion-parameter bilingual asymmetric sequence-to-sequence model, pre-trained from scratch.

This model is fine-tuned from google/mt5-small for converting Romanized Nepali to Nepali text

A Sanskrit-English translation model fine-tuned on T5-small, trained on the itihasa dataset

This model is a fine-tuned version of t5-small on the aslg_pc12 dataset, primarily used for sign language translation tasks.

This model is a fine-tuned English-to-Brazilian Portuguese translation model based on facebook/m2m100_418M on the kde4 dataset

This model is an English-French translation model fine-tuned on the kde4 dataset based on Helsinki-NLP/opus-mt-en-fr, achieving a BLEU score of 52.94 on the evaluation set.

This model is a T5-small architecture fine-tuned on the wmt16 dataset for English to Romanian translation