Commit History
-
Adding `safetensors` variant of this model
Verified signatureThis is an automated PR created with https://huggingface.co/spaces/safetensors/convert This new file is equivalent to `pytorch_model.bin` but safe in the sense that no arbitrary code can be put into it. These files also happen to load much faster than their pytorch counterpart: https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb The widgets on your model page will run using this model even if this is not merged making sure the file actually works. If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions Feel free to ignore this PR.0f9b35e
-
Update README.md
b13b3ca -
Update README.md
a5df403 -
Update README.md
9aa393d -
Update README.md
797261c -
Update README.md
e73934a -
Update README.md
ff2627f
-
Update README.md
42c39bb
-
Update README.md
46ec27e -
Update README.md
5a81333 -
Update README.md
3bea431
-
Update README.md
cf156a6 -
Upload disorBERT_logo.png
d76bf8b -
Update README.md
2fdbefa -
Update README.md
b7365f2 -
Update README.md
f249173 -
Update README.md
492aa1f -
Update README.md
df6525b -
Update README.md
c908e60 -
Update README.md
a8f74ef
-
Update README.md
b8cc10f -
Update README.md
63cca37 -
Update README.md
fb6bcf3 -
Update README.md
0363c13 -
Update README.md
96fec45 -
Update README.md
57a805b -
Update README.md
0c835cc -
Update README.md
cab20eb -
Update README.md
91fb8c3 -
Update README.md
03f3597 -
Update README.md
da581f3 -
Update README.md
bc1470b -
Update README.md
7f8f64b -
Update README.md
6a285bc -
Update README.md
e041fc9 -
Update README.md
9c7291d -
Update README.md
17e9828 -
Update README.md
c605003 -
Update README.md
6604d0e -
Update README.md
a75c070 -
Update README.md
7a72206 -
Update README.md
cbc58fc -
Update README.md
9d2f608 -
Upload README.md
cb20c94 -
Upload README.md
fa897d6 -
Upload disorBERT_logo.png
2d620d0
-
Upload README.md
183589d -
Upload README.md
2c37784
-
Upload 6 files
52c42f9 -
README.md
DisorBERT is a BERT base model trained via double-domain adaptation of a language model. First, we adapted the model to social media language, and then, we adapted it to the mental health domain. In both steps, we incorporated a lexical resource to guide the masking process of the language model and, therefore, to help it in paying more attention to words related to mental disorders. We trained our model for three epochs, using a batch size of 128, a learning rate of 2e^{-5}, on a GPU NVIDIA Tesla V100 32GB SXM2. Paper For more details, refer to the paper DisorbertBERT: A Double Domain Adaptation Model for Detecting Signs of Mental Disorders in Social Media. @inproceedings{aragon-etal-2023-disorbert, title = "{D}isor{BERT}: A Double Domain Adaptation Model for Detecting Signs of Mental Disorders in Social Media", author = "Aragon, Mario and Lopez Monroy, Adrian Pastor and Gonzalez, Luis and Losada, David E. and Montes, Manuel", booktitle = "Pr…d7d91d8