Instructions to use flutter-painter/nllb-fra-fuf-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use flutter-painter/nllb-fra-fuf-v2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="flutter-painter/nllb-fra-fuf-v2")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("flutter-painter/nllb-fra-fuf-v2") model = AutoModelForSeq2SeqLM.from_pretrained("flutter-painter/nllb-fra-fuf-v2") - Notebooks
- Google Colab
- Kaggle
This is a NLLB-200-600M model fine-tuned for translation between French and Fula languages following the unprecedented example shared by slone.
- Fula only covers Guinea / Futa Djalon, not all kinds of fula.
- Dataset = Bible + Quran + Dictionaries and bits, see https://github.com/refacto-org/MaLiNaLi
- bleu fra-fuf = 16
- bleu fuf-fra = 15
- Downloads last month
- 4