Instructions to use christofid/dapbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use christofid/dapbert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="christofid/dapbert")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("christofid/dapbert") model = AutoModelForMaskedLM.from_pretrained("christofid/dapbert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
ab1f582
1
Parent(s): 27ae029
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
### dapBERT
|
| 5 |
+
|
| 6 |
+
DapBERT is a BERT-like model trained based on the domain adaptive pretraining method ([Gururangan et al.](https://aclanthology.org/2020.acl-main.740/)) for the patent domain. Bert-base-uncased is used as base for the training. The training dataset used consists of a corpus of 10,000,000
|
| 7 |
+
patent abstracts that have been filed between 1998-2020 in US and European patent offices as well as the World Intellectual Property Organization.
|