Instructions to use srcocotero/tiny-bert-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use srcocotero/tiny-bert-qa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="srcocotero/tiny-bert-qa")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("srcocotero/tiny-bert-qa") model = AutoModelForQuestionAnswering.from_pretrained("srcocotero/tiny-bert-qa") - Notebooks
- Google Colab
- Kaggle
Commit 路
7e0f890
1
Parent(s): 2ea97db
Upload all_results.json
Browse files- all_results.json +11 -0
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_exact_match": 37.27530747398297,
|
| 4 |
+
"eval_f1": 49.68808218359664,
|
| 5 |
+
"eval_samples": 10626,
|
| 6 |
+
"train_loss": 2.87008975942873,
|
| 7 |
+
"train_runtime": 877.6242,
|
| 8 |
+
"train_samples": 87714,
|
| 9 |
+
"train_samples_per_second": 299.834,
|
| 10 |
+
"train_steps_per_second": 59.968
|
| 11 |
+
}
|