Mitch Naylor
commited on
Commit
·
9fdc17d
1
Parent(s):
ac09500
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,17 @@
|
|
| 1 |
# PsychBERT
|
| 2 |
This domain adapted language model is pretrained from the `bert-base-cased` checkpoint on masked language modeling, using a dataset of ~40,000 PubMed papers in the domain of psychology, psychiatry, mental health, and behavioral health; as well as a dastaset of roughly 200,000 social media conversations about mental health. This work is submitted as an entry for BIBM 2021.
|
| 3 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
Authors: Vedant Vajre, Mitch Naylor, Uday Kamath, Amarda Shehu
|
|
|
|
| 1 |
# PsychBERT
|
| 2 |
This domain adapted language model is pretrained from the `bert-base-cased` checkpoint on masked language modeling, using a dataset of ~40,000 PubMed papers in the domain of psychology, psychiatry, mental health, and behavioral health; as well as a dastaset of roughly 200,000 social media conversations about mental health. This work is submitted as an entry for BIBM 2021.
|
| 3 |
|
| 4 |
+
**Note**: the widget to the right does not work with Flax models. In order to use the model, please pull it into a Python session as follows:
|
| 5 |
+
|
| 6 |
+
```
|
| 7 |
+
from transformers import FlaxAutoModelForMaskedLM, AutoModelForMaskedLM
|
| 8 |
+
|
| 9 |
+
# load as a flax model
|
| 10 |
+
flax_lm = FlaxAutoModelForMaskedLM.from_pretrained('mnaylor/psychbert-cased')
|
| 11 |
+
|
| 12 |
+
# load as a pytorch model
|
| 13 |
+
# requires flax to be installed in your environment
|
| 14 |
+
pytorch_lm = AutoModelForMaskedLM.from_pretrained('mnaylor/psychbert-cased', from_flax=True)
|
| 15 |
+
```
|
| 16 |
+
|
| 17 |
Authors: Vedant Vajre, Mitch Naylor, Uday Kamath, Amarda Shehu
|