You don't have to rely on the models trained so far in COMBO. You can use the included code to train on new corpora and languages, tune to specific usecases or simply retrain larger models with more resources. The scripts in `[examples](src/lambo/examples)` include examples on how to do that:
You don't have to rely on the models trained so far in COMBO. You can use the included code to train on new corpora and languages, tune to specific usecases or simply retrain larger models with more resources. The scripts in [`examples`](src/lambo/examples) include examples on how to do that:
-`run_training.py` -- train simple LAMBO models. This script was used with [UD treebanks](https://universaldependencies.org/#language-) to generate `LAMBO_no_pretraining` models.
-`run_pretraining.py` -- pretrain unsupervised LAMBO models. This script was used with [OSCAR](https://oscar-corpus.com/).
-`run_training_pretrained.py` -- train LAMBO models on UD training data, starting from pretrained models. This script was used to generate `LAMBO` models.