Instructions to use abischoff/word-alignment-de-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abischoff/word-alignment-de-en with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" 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("question-answering", model="abischoff/word-alignment-de-en")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("abischoff/word-alignment-de-en") model = AutoModelForQuestionAnswering.from_pretrained("abischoff/word-alignment-de-en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
word-alignment-de-en
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3212
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 63 | 0.8846 |
| No log | 2.0 | 126 | 0.3864 |
| No log | 3.0 | 189 | 0.3051 |
| No log | 4.0 | 252 | 0.3212 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 5