Instructions to use goaicorp/dyu-translation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use goaicorp/dyu-translation 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="goaicorp/dyu-translation")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("goaicorp/dyu-translation") model = AutoModelForSeq2SeqLM.from_pretrained("goaicorp/dyu-translation", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request access to dyu-translation
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
dyu-translation is shared under CC BY-SA 4.0: it was trained on Koumankan4Dyula by UVCI and Data354. Please read the card, its terms and licenses before requesting access, and make sure you understand them.
Log in or Sign Up to review the conditions and access this model content.
dyu-translation
GO AI Corp's product endpoint for French → Dioula translation. The repo name stays fixed; the model behind it can change.
| Serves | goaicorp/dyu-nllb-600M-fr2dyu: same weights, checked by file hash in November 2026 |
| Published | May 2026 |
Training data, scores and limits are those of dyu-nllb-600M-fr2dyu. This endpoint will be pointed to the best model once all models are re-scored on clean test sets; each change will be listed under Versions.
Résumé en français. Point d'accès « produit » de GO AI Corp pour la traduction français → dioula : le nom du dépôt reste fixe, le modèle servi peut changer. Il sert aujourd'hui
dyu-nllb-600M-fr2dyu(mêmes poids, vérifiés par empreinte des fichiers en novembre 2026) ; données, scores et limites sont ceux de ce modèle. Il sera dirigé vers le meilleur modèle quand tous les modèles auront été réévalués sur des jeux de test propres ; chaque changement sera noté sous Versions. Publié en mai 2026. Licence CC BY-SA 4.0, comme ses données d'entraînement : citez UVCI et Data354 (Koumankan4Dyula) et partagez vos adaptations sous la même licence. Accès sur demande.
Quick start
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
name = "goaicorp/dyu-translation"
tok = AutoTokenizer.from_pretrained(name, src_lang="fra_Latn")
model = AutoModelForSeq2SeqLM.from_pretrained(name)
out = model.generate(**tok("Bonjour", return_tensors="pt"),
forced_bos_token_id=tok.convert_tokens_to_ids("dyu_Latn"), max_new_tokens=128)
print(tok.decode(out[0], skip_special_tokens=True))
Versions
- May 2026: created with the weights of dyu-nllb-600M-fr2dyu.
License
CC BY-SA 4.0, because it was trained on CC BY-SA data (Koumankan4Dyula, UVCI and Data354). Credit them and share adaptations under the same license.
Developed and maintained by
- Wendyellé A. Alban NYANTUDRE: nyantudre@gmail.com
- Aristide BANDAOGO: aristide@goaicorporation.org
- Downloads last month
- 17
Model tree for goaicorp/dyu-translation
Base model
facebook/nllb-200-distilled-600M