eventdata-utd
/

ConfliBERT-scr-uncased

Inference Endpoints

Model card Files Files and versions Community

Edit model card

ConfliBERT is a pre-trained language model for political conflict and violence. We provided four versions of ConfliBERT:

ConfliBERT-scr-uncased: Pretraining from scratch with our own uncased vocabulary (preferred)
ConfliBERT-scr-cased: Pretraining from scratch with our own cased vocabulary
ConfliBERT-cont-uncased: Continual pretraining with original BERT's uncased vocabulary
ConfliBERT-cont-cased: Continual pretraining with original BERT's cased vocabulary

See more details in https://github.com/eventdata/ConfliBERT/

Downloads last month: 14

Safetensors

Model size

109M params

Tensor type

F32

·

Inference Examples

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including eventdata-utd/ConfliBERT-scr-uncased

Model Variants

This collection includes all core variants of the ConfliBERT models, showcasing different training strategies and casing preferences. • 1 item • Updated May 13