Instructions to use Unbabel/XCOMET-XXL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Unbabel/XCOMET-XXL 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-XXL")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Unbabel/XCOMET-XXL", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Updated checkpoints/model.ckpt
#5
by mbilalce - opened
Applied the permanent update using lightening to update the checkpoint from v1.9.4 to v2.4.0 of pytorch lightening.
This was done in response to the error
"Lightning automatically upgraded your loaded checkpoint from v1.9.4 to v2.4.0. To apply the upgrade to your files permanently, run: python -m pytorch_lightning.utilities.upgrade_checkpoint ../ml/model/checkpoints/model.ckpt"
mbilalce changed pull request title from Upload checkpoints/model.ckpt with huggingface_hub to Updated checkpoints/model.ckpt
RicardoRei changed pull request status to merged