Instructions to use Unbabel/XCOMET-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Unbabel/XCOMET-XL 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="Unbabel/XCOMET-XL")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Unbabel/XCOMET-XL", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Model 'Unbabel/XCOMET-XXL' not supported by COMET.
#4
by fcasadome - opened
When trying to run the python script from the model card
Same for XL version
Hi @fcasadome ,
Before you download the model can you pass on this below code and then execute the model download part?
Use your Huggingface Token below:
HUGGING_FACE_TOKEN = ""
!huggingface-cli login --token $HUGGING_FACE_TOKEN
Thank you,
It is working now, I forgot to click the acknowledge button in the model's card