LICENSE
MANIFEST.in
README.md
pyproject.toml
setup.cfg
src/cai_garland/__init__.py
src/cai_garland/data/__init__.py
src/cai_garland/data/context_collator.py
src/cai_garland/data/context_injection_dataset.py
src/cai_garland/data/dataset_infos.json
src/cai_garland/data/parallel_dataset_loader_hf.py
src/cai_garland/data/parallel_dataset_prep.py
src/cai_garland/data/parallel_dataset_sequencing.py
src/cai_garland/data/segmentation_dataset_prep.py
src/cai_garland/data/siamese_collator.py
src/cai_garland/data/synthetic_nllb_data.py
src/cai_garland/data/dataset_prep.config/parallel_dataset_prep.yaml
src/cai_garland/data/dataset_prep.config/segmentation_dataset_prep.yaml
src/cai_garland/data/dataset_prep.config/symbol_cleaning_bo.json
src/cai_garland/data/dataset_prep.config/symbol_cleaning_en.json
src/cai_garland/data/dataset_prep.config/symbol_cleaning_en_no_skip.json
src/cai_garland/data/dataset_prep.config/synthetic_nllb_data.yaml
src/cai_garland/data/dataset_prep.config/output/uncased-no-accents.yaml
src/cai_garland/data/dataset_prep.config/processing/local-dask.yaml
src/cai_garland/data/dataset_prep.config/stages/concatted-registers-sequenced.yaml
src/cai_garland/data/dataset_prep.config/stages/concatted-registers.yaml
src/cai_garland/data/dataset_prep.config/stages/context-embeddings-from-folios-cased.yaml
src/cai_garland/data/dataset_prep.config/stages/context-embeddings-from-folios.yaml
src/cai_garland/data/dataset_prep.config/stages/dictionary.yaml
src/cai_garland/data/dataset_prep.config/stages/folio-registers.yaml
src/cai_garland/data/dataset_prep.config/stages/naive-concats-sequenced-cased.yaml
src/cai_garland/data/dataset_prep.config/stages/naive-concats-sequenced.yaml
src/cai_garland/data/dataset_prep.config/stages/naive-concats.yaml
src/cai_garland/data/dataset_prep.config/stages/naive-unconcatted.yaml
src/cai_garland/data/dataset_prep.config/stages/registers.yaml
src/cai_garland/data/dataset_prep.config/stages/unconcatted-registers-sequenced.yaml
src/cai_garland/data/dataset_prep.config/stages/concat/concat-future-context.yaml
src/cai_garland/data/dataset_prep.config/stages/concat/concat.yaml
src/cai_garland/data/dataset_prep.config/stages/concat/no-concat.yaml
src/cai_garland/data/dataset_prep.config/stages/datasets/84000-full-translations-cased.yaml
src/cai_garland/data/dataset_prep.config/stages/datasets/84000-full-translations.yaml
src/cai_garland/data/dataset_prep.config/stages/datasets/84000-parallel-folios.yaml
src/cai_garland/data/dataset_prep.config/stages/datasets/84000-parallel-sentences.yaml
src/cai_garland/data/dataset_prep.config/stages/datasets/dictionary.yaml
src/cai_garland/data/dataset_prep.config/stages/sequencing/consecutive-cosine.yaml
src/cai_garland/data/dataset_prep.config/stages/sequencing/consecutive-nli.yaml
src/cai_garland/data/dataset_prep.config/stages/sequencing/follows-anywhere.yaml
src/cai_garland/data/dataset_prep.config/stages/sequencing/in-order.yaml
src/cai_garland/data/dataset_prep.config/stages/sequencing/nli.yaml
src/cai_garland/models/__init__.py
src/cai_garland/models/bilingual_tokenizer.py
src/cai_garland/models/cai_encoder_decoder.py
src/cai_garland/models/cai_nllb_tokenizer.py
src/cai_garland/models/factory.py
src/cai_garland/models/pooled_context_decoder_bart.py
src/cai_garland/models/pooled_context_decoder_m2m.py
src/cai_garland/models/siamese_encoder.py
src/cai_garland/training/__init__.py
src/cai_garland/training/cai_trainer_seq2seq.py
src/cai_garland/training/segmenter.py
src/cai_garland/training/train_nmt.py
src/cai_garland/training/segmenter.config/config.yaml
src/cai_garland/training/segmenter.config/training/frequent_logs.yaml
src/cai_garland/training/train_nmt.config/config.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-2-registers-only.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-3-registers-only.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-3-registers.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-no-registers-valid-from-train.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-no-registers.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-raw-no-splits.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-raw-with-bidirectional-context.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-raw-with-context-cased.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-raw-with-context.yaml
src/cai_garland/training/train_nmt.config/data/84000-parallel-sentences-raw.yaml
src/cai_garland/training/train_nmt.config/data/nllb-augmentation-bo-en.yaml
src/cai_garland/training/train_nmt.config/data/nllb-augmentation-bo-it.yaml
src/cai_garland/training/train_nmt.config/dataset_construction/context-injection-cased.yaml
src/cai_garland/training/train_nmt.config/dataset_construction/context-injection.yaml
src/cai_garland/training/train_nmt.config/model/nllb-with-context-for-zst.yaml
src/cai_garland/training/train_nmt.config/model/nllb-with-context.yaml
src/cai_garland/training/train_nmt.config/model/olive-cormorant-bart-pooled-context-injection.yaml
src/cai_garland/training/train_nmt.config/model/olive-cormorant-bart.yaml
src/cai_garland/training/train_nmt.config/model/olive-cormorant-nllb-bidirectional-context.yaml
src/cai_garland/training/train_nmt.config/model/olive-cormorant-nllb-pooled-context-injection-cased.yaml
src/cai_garland/training/train_nmt.config/model/olive-cormorant-nllb-pooled-context-injection.yaml
src/cai_garland/training/train_nmt.config/model/olive-cormorant-nllb.yaml
src/cai_garland/training/train_nmt.config/model/olive-cormorant-x2-bart.yaml
src/cai_garland/training/train_nmt.config/model/olive-cormorant-x3-bart.yaml
src/cai_garland/training/train_nmt.config/training/basic_with_bleu.yaml
src/cai_garland/training/train_nmt.config/training_preprocess/basic.yaml
src/cai_garland/utils/__init__.py
src/cai_garland/utils/segmenters.py
src/cai_garland/utils/str_processors.py
src/cai_garland/utils/translator.py
src/compassionai_garland.egg-info/PKG-INFO
src/compassionai_garland.egg-info/SOURCES.txt
src/compassionai_garland.egg-info/dependency_links.txt
src/compassionai_garland.egg-info/requires.txt
src/compassionai_garland.egg-info/top_level.txt