Instructions to use AdamCodd/distilroberta-squad2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdamCodd/distilroberta-squad2 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="AdamCodd/distilroberta-squad2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("AdamCodd/distilroberta-squad2") model = AutoModelForQuestionAnswering.from_pretrained("AdamCodd/distilroberta-squad2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -52,18 +52,18 @@ Evaluated on the SQuAD 2.0 dev set with the [official eval script](https://works
|
|
| 52 |
|
| 53 |
Results:
|
| 54 |
```
|
| 55 |
-
'exact': 72.
|
| 56 |
-
'f1':
|
| 57 |
'total': 11873,
|
| 58 |
-
'HasAns_exact': 72.
|
| 59 |
-
'HasAns_f1': 78.
|
| 60 |
'HasAns_total': 5928,
|
| 61 |
-
'NoAns_exact':
|
| 62 |
-
'NoAns_f1':
|
| 63 |
'NoAns_total': 5945,
|
| 64 |
-
'best_exact': 72.
|
| 65 |
'best_exact_thresh': 0.0,
|
| 66 |
-
'best_f1':
|
| 67 |
'best_f1_thresh': 0.0
|
| 68 |
```
|
| 69 |
|
|
|
|
| 52 |
|
| 53 |
Results:
|
| 54 |
```
|
| 55 |
+
'exact': 72.9470226564474,
|
| 56 |
+
'f1': 76.03522762032603,
|
| 57 |
'total': 11873,
|
| 58 |
+
'HasAns_exact': 72.4527665317139,
|
| 59 |
+
'HasAns_f1': 78.63803264779528,
|
| 60 |
'HasAns_total': 5928,
|
| 61 |
+
'NoAns_exact': 73.43986543313709,
|
| 62 |
+
'NoAns_f1': 73.43986543313709,
|
| 63 |
'NoAns_total': 5945,
|
| 64 |
+
'best_exact': 72.95544512760044,
|
| 65 |
'best_exact_thresh': 0.0,
|
| 66 |
+
'best_f1': 76.04365009147917,
|
| 67 |
'best_f1_thresh': 0.0
|
| 68 |
```
|
| 69 |
|