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
Support of numpy 2.x and protobuf 5.2x ?
👍 1
#6 opened 10 months ago
by
raptorkwok
Model checkpoint loading throws an error
#5 opened almost 2 years ago
by
alvations
Model 'Unbabel/XCOMET-XXL' not supported by COMET.
3
#4 opened almost 2 years ago
by
fcasadome
Quantization
#3 opened almost 2 years ago
by
laelhalawani