A sarcasm detector built in an hour. Base model is microsoft/deberta-v3-base.

Training Dataset: Sarcasm Corpus V2 - Oraby, Vrindavan Harrison, Lena Reed, Ernesto Hernandez, Ellen Riloff and Marilyn Walker. "Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue." In The 17th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL), Los Angeles, California, USA, 2016.

Downloads last month: 16

Safetensors

Model size

184M params

Tensor type

F32

Inference Examples

Text Classification

Inference API (serverless) is not available, repository is disabled.