RoBERTa for binary sequence classification fine-tuned to classify text derived from herbarium packets as location sensitive. Fine-tuned with 500,000 cleaned data samples from RBG Kew's Herbarium dataset available on GBIF (https://doi.org/10.15468/ly60bx). Trained primarily for English language but may work with other languages due to the large variety of text present in the Kew Herbarium.

Downloads last month: 4

Safetensors

Model size

125M params

Tensor type

F32

Inference Examples

Text Classification

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.