Instructions to use laurievb/OpenLID-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- fastText
How to use laurievb/OpenLID-v2 with fastText:
from huggingface_hub import hf_hub_download import fasttext model = fasttext.load_model(hf_hub_download("laurievb/OpenLID-v2", "model.bin")) - Notebooks
- Google Colab
- Kaggle
add link to temperature sampling
Browse files
README.md
CHANGED
|
@@ -57,7 +57,7 @@ Our work aims to broaden NLP coverage by allowing practitioners to identify rele
|
|
| 57 |
|
| 58 |
## Training data
|
| 59 |
|
| 60 |
-
The model was trained on the [OpenLID-v2 dataset](https://huggingface.co/datasets/laurievb/OpenLID-v2).
|
| 61 |
|
| 62 |
## Training procedure
|
| 63 |
|
|
|
|
| 57 |
|
| 58 |
## Training data
|
| 59 |
|
| 60 |
+
The model was trained on the [OpenLID-v2 dataset](https://huggingface.co/datasets/laurievb/OpenLID-v2). Classes were up/downsampled with temperature sampling prior to training; code to do this can be found [in the `scripts` directory](scripts/prepare_openlid_v2_for_model_training.sh).
|
| 61 |
|
| 62 |
## Training procedure
|
| 63 |
|