--- language: - nb - no license: apache-2.0 library_name: transformers tags: - norwegian - bokmal - bokmål - morphology - normform - text2text-generation pipeline_tag: text-generation --- # NormForm Bokmål Two-Task Model (`NbAiLab/normform-bokmaal-multitask`) > **Experimental Release (`v0.1`)**: Part of the [NormForm](https://github.com/NationalLibraryOfNorway/normform) toolkit for context-aware Norwegian morphological standardization, alternative generation, and sub-norm consistency auditing. This two-task `T5Gemma2` sequence-to-sequence model handles: 1. **`create_morphological_alternatives:`** — Expands Norwegian Bokmål sentences into contextually valid `[alt1|alt2]` morphological alternative lattices while preserving all non-alternative text byte-for-byte. 2. **`skriv_i_samme_morfologiske_stil:`** — Resolves `[alt1|alt2]` morphological lattices into a consistent target sub-norm style conditioned on steering prompt words. ## Quick Start with `normform` Install the [`normform`](https://pypi.org/project/normform/) package (which wraps this model with strict `Template.align` lattice validation and the official reviewed [`NbAiLab/normform-bokmaal-redaksjonsnorm`](https://huggingface.co/datasets/NbAiLab/normform-bokmaal-redaksjonsnorm) style cache): ```bash pip install normform # Standardize Bokmål text using Redaksjonsnorm: normform standardize -t "Jenten kasta boken og så på klokka utenfor sykehuset." --lang nob --style redaksjonsnorm # -> Jenta kastet boka og så på klokken utafor sjukehuset. # Generate [alt1|alt2] morphological alternative brackets: normform alternatives -t "Katta ligger på matta." --lang nob # -> [Katta|Katten] ligger på [matta|matten]. # Audit a document for internal sub-norm inconsistencies: normform audit -i manuscript.txt --lang nob --raw ``` ### Python API ```python from normform import Standardizer std = Standardizer(lang="nob", style="redaksjonsnorm") print(std("Jenten kasta boken og så på klokka utenfor sykehuset.")) # -> "Jenta kastet boka og så på klokken utafor sjukehuset." ``` ## Model Provenance - **Base Model**: `google/t5gemma-2-1b-1b@dd0a2683227859151b1730ca3a63087df5b5f39b` - **Training Checkpoint**: Final step (`47,544`; 3 epochs) of the production two-task SFT run on `NbAiLab/nb-asr-morfologiske-oppgaver-nob-r1@4fca7b0d21c7d61114322622be9e65c824c70001`. - **Official Companion Style Cache**: [`NbAiLab/normform-bokmaal-redaksjonsnorm`](https://huggingface.co/datasets/NbAiLab/normform-bokmaal-redaksjonsnorm)