Instructions to use clips/contact with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use clips/contact with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="clips/contact")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("clips/contact") model = AutoModel.from_pretrained("clips/contact") - Notebooks
- Google Colab
- Kaggle
Commit ·
c87cdce
1
Parent(s): 751002f
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ The model was developed with the intention of achieving high results on NLP task
|
|
| 10 |
|
| 11 |
### How to use
|
| 12 |
|
| 13 |
-
CoNTACT should be fine-tuned on a downstream task. This can be achieved by referring to ```clips/contact``` in the ```--
|
| 14 |
|
| 15 |
```
|
| 16 |
from transformers import AutoModel, AutoTokenizer
|
|
|
|
| 10 |
|
| 11 |
### How to use
|
| 12 |
|
| 13 |
+
CoNTACT should be fine-tuned on a downstream task. This can be achieved by referring to ```clips/contact``` in the ```--model_name_or_path``` argument in Huggingface/Transformers' example scripts, or by loading CoNTACT (as shown below) and fine-tuning it using your own code:
|
| 14 |
|
| 15 |
```
|
| 16 |
from transformers import AutoModel, AutoTokenizer
|