Instructions to use eole-nlp/wmt22-cometkiwi-da-eole with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- COMET
How to use eole-nlp/wmt22-cometkiwi-da-eole with COMET:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
WMT22 COMET-KIWI DA (EOLE)
This is Unbabel/wmt22-cometkiwi-da converted to EOLE format.
No model weights were modified. This repository contains a format conversion for use with EOLE's native transformer_encoder_scorer implementation.
This is not an upstream unbabel-comet checkpoint layout. Use it with EOLE.
Model Details
| Original model | Unbabel/wmt22-cometkiwi-da |
| EOLE architecture | transformer_encoder_scorer |
| Scoring type | comet |
| Class identifier | unified_metric |
| EOLE scorer | EOLE-COMET-KIWI |
| Requires reference | No |
| Encoder | XLM-R large style encoder |
Usage
Requires an EOLE version with native COMET scorer support.
Validation Metric
valid_metrics: ["EOLE-COMET-KIWI"]
comet_model: eole-nlp/wmt22-cometkiwi-da-eole
comet_batch_size: 64
Direct Scoring
COMET-KIWI is reference-free. Use --src for source sentences and --tgt for machine translations.
eole predict \
--model_path eole-nlp/wmt22-cometkiwi-da-eole \
--src /path/to/src.txt \
--tgt /path/to/mt.txt \
--output /path/to/scores.txt \
--with_score
By default, direct scoring writes one segment score per input line. To emit a
single aggregate system score, add --score_level system:
eole predict \
--model_path eole-nlp/wmt22-cometkiwi-da-eole \
--src /path/to/src.txt \
--tgt /path/to/mt.txt \
--output /path/to/system-score.txt \
--with_score \
--score_level system
score_level: system writes one numeric line containing the arithmetic mean of
the segment scores, similar to Unbabel COMET's --only_system mode but using
EOLE's score-file format.
Conversion
Converted with:
eole convert COMET \
--model Unbabel/wmt22-cometkiwi-da \
--output wmt22-cometkiwi-da-eole
Parity
This conversion was parity-checked against the upstream Unbabel COMET runtime. On a 100-line WMT17 slice, native EOLE scoring matched the upstream baseline within floating point tolerance:
| Metric | Value |
|---|---|
| System score delta | 1.01e-08 |
| Sentence MAE | 1.28e-07 |
| Sentence max abs | 9.54e-07 |
Original Model and Attribution
This model is a conversion of Unbabel/wmt22-cometkiwi-da. The model weights were converted without modification.
This converted repository follows the upstream model license: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC-BY-NC-SA-4.0). Use is subject to the upstream non-commercial, attribution, and share-alike terms. Please refer to the original model card and license for training data, intended use, limitations, and citation details.
Unbabel COMET: https://github.com/Unbabel/COMET
- Downloads last month
- 13