Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,23 @@ DepBERT is a domain adaptation of a BERT language model adapted to the depressio
|
|
| 15 |
We follow the standard procedure for fine-tuning a masked language model in [Huggingface’s NLP Course](https://huggingface.co/learn/nlp-course/chapter7/3?fw=pt) 🤗.
|
| 16 |
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
# Paper
|
| 20 |
|
|
|
|
| 15 |
We follow the standard procedure for fine-tuning a masked language model in [Huggingface’s NLP Course](https://huggingface.co/learn/nlp-course/chapter7/3?fw=pt) 🤗.
|
| 16 |
|
| 17 |
|
| 18 |
+
# Usage
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
### Use a pipeline as a high-level helper
|
| 22 |
+
```
|
| 23 |
+
from transformers import pipeline
|
| 24 |
+
|
| 25 |
+
pipe = pipeline("fill-mask", model="citiusLTL/DepBERT")
|
| 26 |
+
```
|
| 27 |
+
### Load model directly
|
| 28 |
+
```
|
| 29 |
+
from transformers import AutoTokenizer, AutoModelForMaskedLM
|
| 30 |
+
|
| 31 |
+
tokenizer = AutoTokenizer.from_pretrained("citiusLTL/DepBERT")
|
| 32 |
+
model = AutoModelForMaskedLM.from_pretrained("citiusLTL/DepBERT")
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
|
| 36 |
# Paper
|
| 37 |
|