Instructions to use Recognai/selectra_medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Recognai/selectra_medium with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForPreTraining tokenizer = AutoTokenizer.from_pretrained("Recognai/selectra_medium") model = AutoModelForPreTraining.from_pretrained("Recognai/selectra_medium") - Notebooks
- Google Colab
- Kaggle
David commited on
Commit ·
f5efd65
1
Parent(s): 17e0fad
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ We release a `small` and `medium` version with the following configuration:
|
|
| 17 |
| [SELECTRA small](https://huggingface.co/Recognai/selectra_small) | 12 | 256 | 22M | 50k | 512 | True |
|
| 18 |
| **SELECTRA medium** | **12** | **384** | **41M** | **50k** | **512** | **True** |
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
## Usage
|
| 23 |
|
|
|
|
| 17 |
| [SELECTRA small](https://huggingface.co/Recognai/selectra_small) | 12 | 256 | 22M | 50k | 512 | True |
|
| 18 |
| **SELECTRA medium** | **12** | **384** | **41M** | **50k** | **512** | **True** |
|
| 19 |
|
| 20 |
+
**SELECTRA small (medium) is about 5 (3) times smaller than BETO but achieves comparable results** (see Metrics section below).
|
| 21 |
|
| 22 |
## Usage
|
| 23 |
|