metadata
license: bigscience-bloom-rail-1.0
Foody BERT
Foody-bert results from the second round of fine-tuning on the text classification task. Continuation of fine-tuning of senty-bert (https://huggingface.co/rttl-ai/senty-bert), which is fine-tuned on yelp reviews and Stanford sentiment treebank with ternary labels (neutral, positive, negative). A foody-bert fine-tuned on DynaSent Bench Data (https://github.com/cgpotts/dynasent), which has more adversarial examples. The dataset mainly contains restaurant review data.