Instructions to use niklaspm/linkbert-base-finetuned-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use niklaspm/linkbert-base-finetuned-squad 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="niklaspm/linkbert-base-finetuned-squad")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("niklaspm/linkbert-base-finetuned-squad") model = AutoModelForQuestionAnswering.from_pretrained("niklaspm/linkbert-base-finetuned-squad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Niklas commited on
Commit 路
f4e3fbf
1
Parent(s): 13ad528
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,3 +5,7 @@ license: apache-2.0
|
|
| 5 |
**Exact Match** 83.19
|
| 6 |
|
| 7 |
**F1** 90.46
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
**Exact Match** 83.19
|
| 6 |
|
| 7 |
**F1** 90.46
|
| 8 |
+
|
| 9 |
+
Checkout [linkbert-large-finetuned-squad](https://huggingface.co/niklaspm/linkbert-large-finetuned-squad) which achives F1:92.68 and EM:86.5
|
| 10 |
+
|
| 11 |
+
See [LinkBERT Paper](https://arxiv.org/abs/2203.15827)
|