Instructions to use zelcakok/bert-base-squad2-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zelcakok/bert-base-squad2-uncased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="zelcakok/bert-base-squad2-uncased")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("zelcakok/bert-base-squad2-uncased") model = AutoModelForQuestionAnswering.from_pretrained("zelcakok/bert-base-squad2-uncased", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,7 @@ tags:
|
|
| 8 |
- Bert
|
| 9 |
- SQuAD2.0
|
| 10 |
- SQuAD
|
|
|
|
| 11 |
---
|
| 12 |
# Extract QA Model (SQuAD2.0)
|
| 13 |
|
|
@@ -29,6 +30,26 @@ max_query_length = 256
|
|
| 29 |
|
| 30 |
## Latest Result
|
| 31 |
```json
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
{
|
| 33 |
"exact": 73.77242482944496,
|
| 34 |
"f1": 76.83752039897598,
|
|
|
|
| 8 |
- Bert
|
| 9 |
- SQuAD2.0
|
| 10 |
- SQuAD
|
| 11 |
+
pipeline_tag: question-answering
|
| 12 |
---
|
| 13 |
# Extract QA Model (SQuAD2.0)
|
| 14 |
|
|
|
|
| 30 |
|
| 31 |
## Latest Result
|
| 32 |
```json
|
| 33 |
+
// 24 Mar 2023, 19:57
|
| 34 |
+
{
|
| 35 |
+
"exact": 74.12616861787248,
|
| 36 |
+
"f1": 77.34212395572948,
|
| 37 |
+
"total": 11873,
|
| 38 |
+
"HasAns_exact": 72.72267206477733,
|
| 39 |
+
"HasAns_f1": 79.16380528447645,
|
| 40 |
+
"HasAns_total": 5928,
|
| 41 |
+
"NoAns_exact": 75.52565180824222,
|
| 42 |
+
"NoAns_f1": 75.52565180824222,
|
| 43 |
+
"NoAns_total": 5945,
|
| 44 |
+
"best_exact": 74.12616861787248,
|
| 45 |
+
"best_exact_thresh": 0.0,
|
| 46 |
+
"best_f1": 77.34212395572948,
|
| 47 |
+
"best_f1_thresh": 0.0
|
| 48 |
+
}
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
```json
|
| 52 |
+
// 23 Mar 2023
|
| 53 |
{
|
| 54 |
"exact": 73.77242482944496,
|
| 55 |
"f1": 76.83752039897598,
|