Downloads · 30 days
50
1% of all-time downloads
psychbert-cased
mnaylor/psychbert-cased
psychbert-cased is a fill-mask model from mnaylor. Use it when you need the model to fill a missing word. It is set up for transformers.
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 be…
All-time downloads
4.5K
Public
Repo size
433 MB
Likes
10
Trending 1
Repo makeup
Click a slice to open those files.
.msgpack433 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Sep 2, 2021
- SHA
- 735ebaf4
Try a prompt
Model card
From the Hugging Face model README
PsychBERT
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.
Note: the token-prediction widget on this page does not work with Flax models. In order to use the model, please pull it into a Python session as follows:
from transformers import FlaxAutoModelForMaskedLM, AutoModelForMaskedLM
# load as a flax model
flax_lm = FlaxAutoModelForMaskedLM.from_pretrained('mnaylor/psychbert-cased')
# load as a pytorch model
# requires flax to be installed in your environment
pytorch_lm = AutoModelForMaskedLM.from_pretrained('mnaylor/psychbert-cased', from_flax=True)
Authors: Vedant Vajre, Mitch Naylor, Uday Kamath, Amarda Shehu
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- Created
- Mar 2, 2022
- Updated
- Sep 2, 2021