Instructions to use drewoodward/mBART-51 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use drewoodward/mBART-51 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="drewoodward/mBART-51")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("drewoodward/mBART-51") model = AutoModelForSeq2SeqLM.from_pretrained("drewoodward/mBART-51", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signaturee7a7cf4
-
Update README.md
Verified signaturemBART-51 is based on the mBART-Large-51 model from Facebook. This model is made to face the problem that translators have with "code-switching". The research done here is focused on code-switching between English and Spanish.c3f420c
-
Upload tokenizer
Verified signatureeb230a0 -
Upload MBartForConditionalGeneration
Verified signature4f60132
-
initial commit
Verified signatureec24880