Instructions to use approach0/dpr-cotbert-020 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use approach0/dpr-cotbert-020 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="approach0/dpr-cotbert-020")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, DprEncoder tokenizer = AutoTokenizer.from_pretrained("approach0/dpr-cotbert-020") model = DprEncoder.from_pretrained("approach0/dpr-cotbert-020", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,10 +19,10 @@ license: mit
|
|
| 19 |
---
|
| 20 |
|
| 21 |
## About
|
| 22 |
-
This repository is a boilerplate to push a mask-filling model to the HuggingFace Model Hub.
|
| 23 |
|
| 24 |
### Upload to huggingface
|
| 25 |
-
Download your tokenizer, model checkpoints, and optionally the training logs () to the `./ckpt` directory.
|
| 26 |
|
| 27 |
Optionally, test model using the MLM task:
|
| 28 |
```sh
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
## About
|
| 22 |
+
This [repository](https://github.com/approach0/azbert) is a boilerplate to push a mask-filling model to the HuggingFace Model Hub.
|
| 23 |
|
| 24 |
### Upload to huggingface
|
| 25 |
+
Download your tokenizer, model checkpoints, and optionally the training logs (`events.out.*`) to the `./ckpt` directory.
|
| 26 |
|
| 27 |
Optionally, test model using the MLM task:
|
| 28 |
```sh
|