Instructions to use deepset/roberta-base-squad2-distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepset/roberta-base-squad2-distilled with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="deepset/roberta-base-squad2-distilled")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("deepset/roberta-base-squad2-distilled") model = AutoModelForQuestionAnswering.from_pretrained("deepset/roberta-base-squad2-distilled", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit 路
a152f4d
1
Parent(s): 18c01a6
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ tags:
|
|
| 16 |
**Training data:** GermanQuAD train set (~ 12MB)
|
| 17 |
**Eval data:** GermanQuAD test set (~ 5MB)
|
| 18 |
**Infrastructure**: 4x V100 GPU
|
| 19 |
-
**Published**:
|
| 20 |
|
| 21 |
## Details
|
| 22 |
- haystack's distillation feature was used for training. deepset/roberta-large-squad2 was used as the teacher model.
|
|
|
|
| 16 |
**Training data:** GermanQuAD train set (~ 12MB)
|
| 17 |
**Eval data:** GermanQuAD test set (~ 5MB)
|
| 18 |
**Infrastructure**: 4x V100 GPU
|
| 19 |
+
**Published**: Dec 8th, 2021
|
| 20 |
|
| 21 |
## Details
|
| 22 |
- haystack's distillation feature was used for training. deepset/roberta-large-squad2 was used as the teacher model.
|