Downloads · 30 days
31
2% of all-time downloads
CORD19-BERT
CovRelex-SE/CORD19-BERT
CORD19-BERT is a fill-mask model from CovRelex-SE. Use it when you need the model to fill a missing word. It is set up for transformers.
The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 32 - evalbatchsize: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: linear -…
All-time downloads
1.4K
Public
Repo size
876 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jul 14, 2022
- Updated
- Jul 14, 2022
- SHA
- 3fd28418
Try a prompt
Model card
From the Hugging Face model README
CORD19-BERT
How to use
from transformers import BertTokenizer, BertModel
tokenizer = BertTokenizer.from_pretrained('CovRelex-SE/CORD19-BERT')
model = BertModel.from_pretrained("CovRelex-SE/CORD19-BERT")
text = "The virus can spread from an infected person’s mouth or nose."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- Created
- Jul 14, 2022
- Updated
- Jul 14, 2022