Instructions to use globuslabs/ScholarBERT_100_64bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use globuslabs/ScholarBERT_100_64bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="globuslabs/ScholarBERT_100_64bit")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("globuslabs/ScholarBERT_100_64bit") model = AutoModelForMaskedLM.from_pretrained("globuslabs/ScholarBERT_100_64bit") - Notebooks
- Google Colab
- Kaggle
Commit ·
ca44fa0
1
Parent(s): afbd33e
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ tags:
|
|
| 6 |
license: apache-2.0
|
| 7 |
---
|
| 8 |
|
| 9 |
-
#
|
| 10 |
|
| 11 |
This is the **ScholarBERT_100_64bit** variant of the ScholarBERT model family. The difference between this variant and the **ScholarBERT_100** model is that its tokenizer
|
| 12 |
is trained with `int64` rather than the default `int32`, so the count of very frequent tokens (e.g., "the") does not overflow.
|
|
|
|
| 6 |
license: apache-2.0
|
| 7 |
---
|
| 8 |
|
| 9 |
+
# ScholarBERT_100_64bit Model
|
| 10 |
|
| 11 |
This is the **ScholarBERT_100_64bit** variant of the ScholarBERT model family. The difference between this variant and the **ScholarBERT_100** model is that its tokenizer
|
| 12 |
is trained with `int64` rather than the default `int32`, so the count of very frequent tokens (e.g., "the") does not overflow.
|