Instructions to use WindyWord/translate-fr-pon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindyWord/translate-fr-pon 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="WindyWord/translate-fr-pon")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WindyWord/translate-fr-pon", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_id": "windy-pair-fr-pon", | |
| "doctor": "herm0", | |
| "procedure": "ebible_finetune_v3", | |
| "timestamp": "2026-03-28T03:36:25.108183+00:00", | |
| "data_source": "ebible.org", | |
| "training_pairs": 25000, | |
| "base_loss": 8.459190549850463, | |
| "ft_loss": 2.9365317213535307, | |
| "improvement_pct": 65.2859017178016, | |
| "epochs": 1, | |
| "learning_rate": 2e-05, | |
| "batch_size": 16, | |
| "max_length": 128 | |
| } |