Instructions to use WindstormLabs/translate-hil-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindstormLabs/translate-hil-en 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="WindstormLabs/translate-hil-en")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WindstormLabs/translate-hil-en", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_id": "windy-pair-hil-en", | |
| "doctor": "herm0", | |
| "procedure": "ebible_finetune_v3", | |
| "timestamp": "2026-03-28T03:49:22.409561+00:00", | |
| "data_source": "ebible.org", | |
| "training_pairs": 25000, | |
| "base_loss": 9.727687737941743, | |
| "ft_loss": 3.145752620100975, | |
| "improvement_pct": 67.66186677815197, | |
| "epochs": 1, | |
| "learning_rate": 2e-05, | |
| "batch_size": 16, | |
| "max_length": 128 | |
| } |