Instructions to use Nadav/MacSQuAD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nadav/MacSQuAD 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="Nadav/MacSQuAD")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Nadav/MacSQuAD") model = AutoModelForQuestionAnswering.from_pretrained("Nadav/MacSQuAD", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,4 +16,6 @@ training_args = TrainingArguments(
|
|
| 16 |
lr_scheduler_type=SchedulerType.LINEAR,
|
| 17 |
warmup_ratio=0.2
|
| 18 |
)
|
| 19 |
-
```
|
|
|
|
|
|
|
|
|
| 16 |
lr_scheduler_type=SchedulerType.LINEAR,
|
| 17 |
warmup_ratio=0.2
|
| 18 |
)
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
+
{'exact': 49.49886296639434, 'f1': 53.9199170778635, 'total': 11873, 'HasAns_exact': 60.08771929824562, 'HasAns_f1': 68.94250598270429, 'HasAns_total': 5928, 'NoAns_exact': 38.940285954583686, 'NoAns_f1': 38.940285954583686, 'NoAns_total': 5945, 'best_exact': 50.5095595047587, 'best_exact_thresh': 0.0, 'best_f1': 51.75825524534494, 'best_f1_thresh': 0.0}
|